Compare commits
89 Commits
2014.03.27
...
2014.04.04
Author | SHA1 | Date | |
---|---|---|---|
![]() |
d3a96346c4 | ||
![]() |
0e518e2fea | ||
![]() |
1e0a235f39 | ||
![]() |
9ad400f75e | ||
![]() |
3537b93d8a | ||
![]() |
56eca2e956 | ||
![]() |
2ad4d1ba07 | ||
![]() |
4853de808b | ||
![]() |
6ff5f12218 | ||
![]() |
52a180684f | ||
![]() |
b21e25702f | ||
![]() |
983af2600f | ||
![]() |
f34e6a2cd6 | ||
![]() |
a9f304031b | ||
![]() |
9271bc8355 | ||
![]() |
d1b3e3dd75 | ||
![]() |
968ed2a777 | ||
![]() |
24de5d2556 | ||
![]() |
d26e981df4 | ||
![]() |
e45d40b171 | ||
![]() |
4a419b8851 | ||
![]() |
5fbd672c38 | ||
![]() |
bec1fad223 | ||
![]() |
177fed41bc | ||
![]() |
b900e7cba4 | ||
![]() |
14cb4979f0 | ||
![]() |
69e61e30fe | ||
![]() |
cce929eaac | ||
![]() |
b6cfde99b7 | ||
![]() |
1be99f052d | ||
![]() |
2410c43d83 | ||
![]() |
aea6e7fc3c | ||
![]() |
91a76c40c0 | ||
![]() |
d2b194607c | ||
![]() |
f6177462db | ||
![]() |
9ddaf4ef8c | ||
![]() |
97b5573848 | ||
![]() |
18c95c1ab0 | ||
![]() |
0479c625a4 | ||
![]() |
f659951e22 | ||
![]() |
5853a7316e | ||
![]() |
a612753db9 | ||
![]() |
c8fc3fb524 | ||
![]() |
5912c639df | ||
![]() |
017e4dd58c | ||
![]() |
651486621d | ||
![]() |
28d9032c88 | ||
![]() |
16f4eb723a | ||
![]() |
1cbd410620 | ||
![]() |
d41ac5f5dc | ||
![]() |
9c1fc022ae | ||
![]() |
83d548ef0f | ||
![]() |
c72477bd32 | ||
![]() |
9a7b072e38 | ||
![]() |
cbc4a6cc7e | ||
![]() |
cd7481a39e | ||
![]() |
acd213ed6d | ||
![]() |
77ffa95701 | ||
![]() |
2b25cb5d76 | ||
![]() |
62fec3b2ff | ||
![]() |
e79162558e | ||
![]() |
2da67107ee | ||
![]() |
2ff7f8975e | ||
![]() |
87a2566048 | ||
![]() |
986f56736b | ||
![]() |
2583a0308b | ||
![]() |
40c716d2a2 | ||
![]() |
79bfd01001 | ||
![]() |
f2bcdd8e02 | ||
![]() |
8c5850eeb4 | ||
![]() |
bd3e077a2d | ||
![]() |
7e70ac36b3 | ||
![]() |
2cc0082dc0 | ||
![]() |
056b56688a | ||
![]() |
b17418313f | ||
![]() |
e9a6fd6a68 | ||
![]() |
bf30f3bd9d | ||
![]() |
330edf2d84 | ||
![]() |
43f775e4ca | ||
![]() |
8f6562448c | ||
![]() |
263f4b514b | ||
![]() |
f0da3f1ef9 | ||
![]() |
cb3ac1c610 | ||
![]() |
8efd15f477 | ||
![]() |
d26ebe990f | ||
![]() |
28acf5500a | ||
![]() |
214c22c704 | ||
![]() |
8cdafb47b9 | ||
![]() |
0dae5083f1 |
@@ -3,5 +3,4 @@ include test/*.py
|
||||
include test/*.json
|
||||
include youtube-dl.bash-completion
|
||||
include youtube-dl.1
|
||||
recursive-include docs *
|
||||
prune docs/_build
|
||||
recursive-include docs Makefile conf.py *.rst
|
||||
|
67
README.md
67
README.md
@@ -65,6 +65,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
configuration in ~/.config/youtube-dl.conf
|
||||
(%APPDATA%/youtube-dl/config.txt on
|
||||
Windows)
|
||||
--encoding ENCODING Force the specified encoding (experimental)
|
||||
|
||||
## Video Selection:
|
||||
--playlist-start NUMBER playlist video to start at (default is 1)
|
||||
@@ -181,7 +182,9 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--get-duration simulate, quiet but print video length
|
||||
--get-filename simulate, quiet but print output filename
|
||||
--get-format simulate, quiet but print output format
|
||||
-j, --dump-json simulate, quiet but print JSON information
|
||||
-j, --dump-json simulate, quiet but print JSON information.
|
||||
See --output for a description of available
|
||||
keys.
|
||||
--newline output progress bar as new lines
|
||||
--no-progress do not print progress bar
|
||||
--console-title display progress in console titlebar
|
||||
@@ -368,7 +371,67 @@ If you want to create a build of youtube-dl yourself, you'll need
|
||||
|
||||
### Adding support for a new site
|
||||
|
||||
If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
|
||||
If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
|
||||
|
||||
1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
|
||||
2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
|
||||
3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
|
||||
4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
|
||||
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class YourExtractorIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://yourextractor.com/watch/42',
|
||||
'md5': 'TODO: md5 sum of the first 10KiB of the video file',
|
||||
'info_dict': {
|
||||
'id': '42',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video title goes here',
|
||||
# TODO more properties, either as:
|
||||
# * A value
|
||||
# * MD5 checksum; start the string with md5:
|
||||
# * A regular expression; start the string with re:
|
||||
# * Any Python type (for example int or float)
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
# TODO more code goes here, for example ...
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
# TODO more properties (see youtube_dl/extractor/common.py)
|
||||
}
|
||||
|
||||
|
||||
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
|
||||
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done.
|
||||
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
|
||||
8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
|
||||
9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:
|
||||
|
||||
$ git add youtube_dl/extractor/__init__.py
|
||||
$ git add youtube_dl/extractor/yourextractor.py
|
||||
$ git commit -m '[yourextractor] Add new extractor'
|
||||
$ git push origin yourextractor
|
||||
|
||||
10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
|
||||
|
||||
In any case, thank you very much for your contributions!
|
||||
|
||||
# BUGS
|
||||
|
||||
|
@@ -26,16 +26,27 @@ class YDL(FakeYDL):
|
||||
self.msgs.append(msg)
|
||||
|
||||
|
||||
def _make_result(formats, **kwargs):
|
||||
res = {
|
||||
'formats': formats,
|
||||
'id': 'testid',
|
||||
'title': 'testttitle',
|
||||
'extractor': 'testex',
|
||||
}
|
||||
res.update(**kwargs)
|
||||
return res
|
||||
|
||||
|
||||
class TestFormatSelection(unittest.TestCase):
|
||||
def test_prefer_free_formats(self):
|
||||
# Same resolution => download webm
|
||||
ydl = YDL()
|
||||
ydl.params['prefer_free_formats'] = True
|
||||
formats = [
|
||||
{'ext': 'webm', 'height': 460},
|
||||
{'ext': 'mp4', 'height': 460},
|
||||
{'ext': 'webm', 'height': 460, 'url': 'x'},
|
||||
{'ext': 'mp4', 'height': 460, 'url': 'y'},
|
||||
]
|
||||
info_dict = {'formats': formats, 'extractor': 'test'}
|
||||
info_dict = _make_result(formats)
|
||||
yie = YoutubeIE(ydl)
|
||||
yie._sort_formats(info_dict['formats'])
|
||||
ydl.process_ie_result(info_dict)
|
||||
@@ -46,8 +57,8 @@ class TestFormatSelection(unittest.TestCase):
|
||||
ydl = YDL()
|
||||
ydl.params['prefer_free_formats'] = True
|
||||
formats = [
|
||||
{'ext': 'webm', 'height': 720},
|
||||
{'ext': 'mp4', 'height': 1080},
|
||||
{'ext': 'webm', 'height': 720, 'url': 'a'},
|
||||
{'ext': 'mp4', 'height': 1080, 'url': 'b'},
|
||||
]
|
||||
info_dict['formats'] = formats
|
||||
yie = YoutubeIE(ydl)
|
||||
@@ -60,9 +71,9 @@ class TestFormatSelection(unittest.TestCase):
|
||||
ydl = YDL()
|
||||
ydl.params['prefer_free_formats'] = False
|
||||
formats = [
|
||||
{'ext': 'webm', 'height': 720},
|
||||
{'ext': 'mp4', 'height': 720},
|
||||
{'ext': 'flv', 'height': 720},
|
||||
{'ext': 'webm', 'height': 720, 'url': '_'},
|
||||
{'ext': 'mp4', 'height': 720, 'url': '_'},
|
||||
{'ext': 'flv', 'height': 720, 'url': '_'},
|
||||
]
|
||||
info_dict['formats'] = formats
|
||||
yie = YoutubeIE(ydl)
|
||||
@@ -74,8 +85,8 @@ class TestFormatSelection(unittest.TestCase):
|
||||
ydl = YDL()
|
||||
ydl.params['prefer_free_formats'] = False
|
||||
formats = [
|
||||
{'ext': 'flv', 'height': 720},
|
||||
{'ext': 'webm', 'height': 720},
|
||||
{'ext': 'flv', 'height': 720, 'url': '_'},
|
||||
{'ext': 'webm', 'height': 720, 'url': '_'},
|
||||
]
|
||||
info_dict['formats'] = formats
|
||||
yie = YoutubeIE(ydl)
|
||||
@@ -91,8 +102,7 @@ class TestFormatSelection(unittest.TestCase):
|
||||
{'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
|
||||
{'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
|
||||
]
|
||||
info_dict = {
|
||||
'formats': formats, 'extractor': 'test', 'id': 'testvid'}
|
||||
info_dict = _make_result(formats)
|
||||
|
||||
ydl = YDL()
|
||||
ydl.process_ie_result(info_dict)
|
||||
@@ -120,12 +130,12 @@ class TestFormatSelection(unittest.TestCase):
|
||||
|
||||
def test_format_selection(self):
|
||||
formats = [
|
||||
{'format_id': '35', 'ext': 'mp4', 'preference': 1},
|
||||
{'format_id': '45', 'ext': 'webm', 'preference': 2},
|
||||
{'format_id': '47', 'ext': 'webm', 'preference': 3},
|
||||
{'format_id': '2', 'ext': 'flv', 'preference': 4},
|
||||
{'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
|
||||
{'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
|
||||
{'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
|
||||
{'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
|
||||
]
|
||||
info_dict = {'formats': formats, 'extractor': 'test'}
|
||||
info_dict = _make_result(formats)
|
||||
|
||||
ydl = YDL({'format': '20/47'})
|
||||
ydl.process_ie_result(info_dict.copy())
|
||||
@@ -154,12 +164,12 @@ class TestFormatSelection(unittest.TestCase):
|
||||
|
||||
def test_format_selection_audio(self):
|
||||
formats = [
|
||||
{'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none'},
|
||||
{'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none'},
|
||||
{'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none'},
|
||||
{'format_id': 'vid', 'ext': 'mp4', 'preference': 4},
|
||||
{'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
|
||||
{'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
|
||||
{'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
|
||||
{'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
|
||||
]
|
||||
info_dict = {'formats': formats, 'extractor': 'test'}
|
||||
info_dict = _make_result(formats)
|
||||
|
||||
ydl = YDL({'format': 'bestaudio'})
|
||||
ydl.process_ie_result(info_dict.copy())
|
||||
@@ -172,10 +182,10 @@ class TestFormatSelection(unittest.TestCase):
|
||||
self.assertEqual(downloaded['format_id'], 'audio-low')
|
||||
|
||||
formats = [
|
||||
{'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1},
|
||||
{'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2},
|
||||
{'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
|
||||
{'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
|
||||
]
|
||||
info_dict = {'formats': formats, 'extractor': 'test'}
|
||||
info_dict = _make_result(formats)
|
||||
|
||||
ydl = YDL({'format': 'bestaudio/worstaudio/best'})
|
||||
ydl.process_ie_result(info_dict.copy())
|
||||
@@ -184,11 +194,11 @@ class TestFormatSelection(unittest.TestCase):
|
||||
|
||||
def test_format_selection_video(self):
|
||||
formats = [
|
||||
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none'},
|
||||
{'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none'},
|
||||
{'format_id': 'vid', 'ext': 'mp4', 'preference': 3},
|
||||
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
|
||||
{'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
|
||||
{'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
|
||||
]
|
||||
info_dict = {'formats': formats, 'extractor': 'test'}
|
||||
info_dict = _make_result(formats)
|
||||
|
||||
ydl = YDL({'format': 'bestvideo'})
|
||||
ydl.process_ie_result(info_dict.copy())
|
||||
@@ -217,10 +227,12 @@ class TestFormatSelection(unittest.TestCase):
|
||||
for f1id, f2id in zip(order, order[1:]):
|
||||
f1 = YoutubeIE._formats[f1id].copy()
|
||||
f1['format_id'] = f1id
|
||||
f1['url'] = 'url:' + f1id
|
||||
f2 = YoutubeIE._formats[f2id].copy()
|
||||
f2['format_id'] = f2id
|
||||
f2['url'] = 'url:' + f2id
|
||||
|
||||
info_dict = {'formats': [f1, f2], 'extractor': 'youtube'}
|
||||
info_dict = _make_result([f1, f2], extractor='youtube')
|
||||
ydl = YDL()
|
||||
yie = YoutubeIE(ydl)
|
||||
yie._sort_formats(info_dict['formats'])
|
||||
@@ -228,7 +240,7 @@ class TestFormatSelection(unittest.TestCase):
|
||||
downloaded = ydl.downloaded_info_dicts[0]
|
||||
self.assertEqual(downloaded['format_id'], f1id)
|
||||
|
||||
info_dict = {'formats': [f2, f1], 'extractor': 'youtube'}
|
||||
info_dict = _make_result([f2, f1], extractor='youtube')
|
||||
ydl = YDL()
|
||||
yie = YoutubeIE(ydl)
|
||||
yie._sort_formats(info_dict['formats'])
|
||||
|
@@ -144,7 +144,18 @@ class TestAllURLsMatching(unittest.TestCase):
|
||||
self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
|
||||
|
||||
def test_ComedyCentralShows(self):
|
||||
self.assertMatch('http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview', ['ComedyCentralShows'])
|
||||
self.assertMatch(
|
||||
'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
|
||||
['ComedyCentralShows'])
|
||||
self.assertMatch(
|
||||
'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
|
||||
['ComedyCentralShows'])
|
||||
self.assertMatch(
|
||||
'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
|
||||
['ComedyCentralShows'])
|
||||
self.assertMatch(
|
||||
'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
|
||||
['ComedyCentralShows'])
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
@@ -42,6 +42,7 @@ from youtube_dl.extractor import (
|
||||
ToypicsUserIE,
|
||||
XTubeUserIE,
|
||||
InstagramUserIE,
|
||||
CSpanIE,
|
||||
)
|
||||
|
||||
|
||||
@@ -314,6 +315,19 @@ class TestPlaylists(unittest.TestCase):
|
||||
}
|
||||
expect_info_dict(self, EXPECTED, test_video)
|
||||
|
||||
def test_CSpan_playlist(self):
|
||||
dl = FakeYDL()
|
||||
ie = CSpanIE(dl)
|
||||
result = ie.extract(
|
||||
'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall')
|
||||
self.assertIsPlaylist(result)
|
||||
self.assertEqual(result['id'], '342759')
|
||||
self.assertEqual(
|
||||
result['title'], 'General Motors Ignition Switch Recall')
|
||||
self.assertEqual(len(result['entries']), 9)
|
||||
whole_duration = sum(e['duration'] for e in result['entries'])
|
||||
self.assertEqual(whole_duration, 14855)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
@@ -8,6 +8,7 @@ import datetime
|
||||
import errno
|
||||
import io
|
||||
import json
|
||||
import locale
|
||||
import os
|
||||
import platform
|
||||
import re
|
||||
@@ -159,6 +160,7 @@ class YoutubeDL(object):
|
||||
include_ads: Download ads as well
|
||||
default_search: Prepend this string if an input url is not valid.
|
||||
'auto' for elaborate guessing
|
||||
encoding: Use this encoding instead of the system-specified.
|
||||
|
||||
The following parameters are not used by YoutubeDL itself, they are used by
|
||||
the FileDownloader:
|
||||
@@ -700,6 +702,11 @@ class YoutubeDL(object):
|
||||
def process_video_result(self, info_dict, download=True):
|
||||
assert info_dict.get('_type', 'video') == 'video'
|
||||
|
||||
if 'id' not in info_dict:
|
||||
raise ExtractorError('Missing "id" field in extractor result')
|
||||
if 'title' not in info_dict:
|
||||
raise ExtractorError('Missing "title" field in extractor result')
|
||||
|
||||
if 'playlist' not in info_dict:
|
||||
# It isn't part of a playlist
|
||||
info_dict['playlist'] = None
|
||||
@@ -731,6 +738,9 @@ class YoutubeDL(object):
|
||||
|
||||
# We check that all the formats have the format and format_id fields
|
||||
for i, format in enumerate(formats):
|
||||
if 'url' not in format:
|
||||
raise ExtractorError('Missing "url" key in result (index %d)' % i)
|
||||
|
||||
if format.get('format_id') is None:
|
||||
format['format_id'] = compat_str(i)
|
||||
if format.get('format') is None:
|
||||
@@ -741,7 +751,7 @@ class YoutubeDL(object):
|
||||
)
|
||||
# Automatically determine file extension if missing
|
||||
if 'ext' not in format:
|
||||
format['ext'] = determine_ext(format['url'])
|
||||
format['ext'] = determine_ext(format['url']).lower()
|
||||
|
||||
format_limit = self.params.get('format_limit', None)
|
||||
if format_limit:
|
||||
@@ -866,7 +876,7 @@ class YoutubeDL(object):
|
||||
|
||||
try:
|
||||
dn = os.path.dirname(encodeFilename(filename))
|
||||
if dn != '' and not os.path.exists(dn):
|
||||
if dn and not os.path.exists(dn):
|
||||
os.makedirs(dn)
|
||||
except (OSError, IOError) as err:
|
||||
self.report_error('unable to create directory ' + compat_str(err))
|
||||
@@ -1200,6 +1210,9 @@ class YoutubeDL(object):
|
||||
def print_debug_header(self):
|
||||
if not self.params.get('verbose'):
|
||||
return
|
||||
|
||||
write_string('[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' %
|
||||
(locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, self.get_encoding()))
|
||||
write_string('[debug] youtube-dl version ' + __version__ + '\n')
|
||||
try:
|
||||
sp = subprocess.Popen(
|
||||
@@ -1264,3 +1277,19 @@ class YoutubeDL(object):
|
||||
# (See https://github.com/rg3/youtube-dl/issues/1309 for details)
|
||||
opener.addheaders = []
|
||||
self._opener = opener
|
||||
|
||||
def encode(self, s):
|
||||
if isinstance(s, bytes):
|
||||
return s # Already encoded
|
||||
|
||||
try:
|
||||
return s.encode(self.get_encoding())
|
||||
except UnicodeEncodeError as err:
|
||||
err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.'
|
||||
raise
|
||||
|
||||
def get_encoding(self):
|
||||
encoding = self.params.get('encoding')
|
||||
if encoding is None:
|
||||
encoding = preferredencoding()
|
||||
return encoding
|
||||
|
@@ -51,6 +51,7 @@ __authors__ = (
|
||||
'David Wagner',
|
||||
'Juan C. Olivares',
|
||||
'Mattias Harrysson',
|
||||
'phaer',
|
||||
)
|
||||
|
||||
__license__ = 'Public Domain'
|
||||
@@ -255,13 +256,17 @@ def parseOpts(overrideArguments=None):
|
||||
general.add_option(
|
||||
'--bidi-workaround', dest='bidi_workaround', action='store_true',
|
||||
help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
|
||||
general.add_option('--default-search',
|
||||
dest='default_search', metavar='PREFIX',
|
||||
help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
|
||||
general.add_option(
|
||||
'--default-search',
|
||||
dest='default_search', metavar='PREFIX',
|
||||
help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
|
||||
general.add_option(
|
||||
'--ignore-config',
|
||||
action='store_true',
|
||||
help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
|
||||
general.add_option(
|
||||
'--encoding', dest='encoding', metavar='ENCODING',
|
||||
help='Force the specified encoding (experimental)')
|
||||
|
||||
selection.add_option(
|
||||
'--playlist-start',
|
||||
@@ -395,7 +400,7 @@ def parseOpts(overrideArguments=None):
|
||||
help='simulate, quiet but print output format', default=False)
|
||||
verbosity.add_option('-j', '--dump-json',
|
||||
action='store_true', dest='dumpjson',
|
||||
help='simulate, quiet but print JSON information', default=False)
|
||||
help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False)
|
||||
verbosity.add_option('--newline',
|
||||
action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
|
||||
verbosity.add_option('--no-progress',
|
||||
@@ -539,8 +544,6 @@ def parseOpts(overrideArguments=None):
|
||||
write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
|
||||
write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
|
||||
write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
|
||||
write_string(u'[debug] Encodings: locale %r, fs %r, out %r, pref: %r\n' %
|
||||
(locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, preferredencoding()))
|
||||
|
||||
return parser, opts, args
|
||||
|
||||
@@ -674,7 +677,7 @@ def _real_main(argv=None):
|
||||
date = DateRange.day(opts.date)
|
||||
else:
|
||||
date = DateRange(opts.dateafter, opts.datebefore)
|
||||
if opts.default_search not in ('auto', None) and ':' not in opts.default_search:
|
||||
if opts.default_search not in ('auto', 'auto_warning', None) and ':' not in opts.default_search:
|
||||
parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
|
||||
|
||||
# Do not download videos when there are audio-only formats
|
||||
@@ -785,6 +788,7 @@ def _real_main(argv=None):
|
||||
'include_ads': opts.include_ads,
|
||||
'default_search': opts.default_search,
|
||||
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
|
||||
'encoding': opts.encoding,
|
||||
}
|
||||
|
||||
with YoutubeDL(ydl_opts) as ydl:
|
||||
|
@@ -297,6 +297,7 @@ class F4mFD(FileDownloader):
|
||||
break
|
||||
frags_filenames.append(frag_filename)
|
||||
|
||||
dest_stream.close()
|
||||
self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
|
||||
|
||||
self.try_rename(tmpfilename, filename)
|
||||
|
@@ -40,6 +40,7 @@ from .clipfish import ClipfishIE
|
||||
from .cliphunter import CliphunterIE
|
||||
from .clipsyndicate import ClipsyndicateIE
|
||||
from .cmt import CMTIE
|
||||
from .cnet import CNETIE
|
||||
from .cnn import (
|
||||
CNNIE,
|
||||
CNNBlogsIE,
|
||||
@@ -83,6 +84,7 @@ from .fktv import (
|
||||
)
|
||||
from .flickr import FlickrIE
|
||||
from .fourtube import FourTubeIE
|
||||
from .franceculture import FranceCultureIE
|
||||
from .franceinter import FranceInterIE
|
||||
from .francetv import (
|
||||
PluzzIE,
|
||||
@@ -152,10 +154,13 @@ from .mixcloud import MixcloudIE
|
||||
from .mpora import MporaIE
|
||||
from .mofosex import MofosexIE
|
||||
from .mooshare import MooshareIE
|
||||
from .morningstar import MorningstarIE
|
||||
from .motorsport import MotorsportIE
|
||||
from .mtv import (
|
||||
MTVIE,
|
||||
MTVIggyIE,
|
||||
)
|
||||
from .musicplayon import MusicPlayOnIE
|
||||
from .muzu import MuzuTVIE
|
||||
from .myspace import MySpaceIE
|
||||
from .myspass import MySpassIE
|
||||
@@ -177,6 +182,8 @@ from .normalboots import NormalbootsIE
|
||||
from .novamov import NovaMovIE
|
||||
from .nowness import NownessIE
|
||||
from .nowvideo import NowVideoIE
|
||||
from .ntv import NTVIE
|
||||
from .oe1 import OE1IE
|
||||
from .ooyala import OoyalaIE
|
||||
from .orf import ORFIE
|
||||
from .parliamentliveuk import ParliamentLiveUKIE
|
||||
@@ -283,7 +290,10 @@ from .vk import VKIE
|
||||
from .vube import VubeIE
|
||||
from .washingtonpost import WashingtonPostIE
|
||||
from .wat import WatIE
|
||||
from .wdr import WDRIE
|
||||
from .wdr import (
|
||||
WDRIE,
|
||||
WDRMausIE,
|
||||
)
|
||||
from .weibo import WeiboIE
|
||||
from .wimp import WimpIE
|
||||
from .wistia import WistiaIE
|
||||
|
@@ -6,7 +6,6 @@ import json
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urlparse,
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
|
||||
@@ -16,9 +15,10 @@ class AppleTrailersIE(InfoExtractor):
|
||||
"url": "http://trailers.apple.com/trailers/wb/manofsteel/",
|
||||
"playlist": [
|
||||
{
|
||||
"file": "manofsteel-trailer4.mov",
|
||||
"md5": "d97a8e575432dbcb81b7c3acb741f8a8",
|
||||
"info_dict": {
|
||||
"id": "manofsteel-trailer4",
|
||||
"ext": "mov",
|
||||
"duration": 111,
|
||||
"title": "Trailer 4",
|
||||
"upload_date": "20130523",
|
||||
@@ -26,9 +26,10 @@ class AppleTrailersIE(InfoExtractor):
|
||||
},
|
||||
},
|
||||
{
|
||||
"file": "manofsteel-trailer3.mov",
|
||||
"md5": "b8017b7131b721fb4e8d6f49e1df908c",
|
||||
"info_dict": {
|
||||
"id": "manofsteel-trailer3",
|
||||
"ext": "mov",
|
||||
"duration": 182,
|
||||
"title": "Trailer 3",
|
||||
"upload_date": "20130417",
|
||||
@@ -36,9 +37,10 @@ class AppleTrailersIE(InfoExtractor):
|
||||
},
|
||||
},
|
||||
{
|
||||
"file": "manofsteel-trailer.mov",
|
||||
"md5": "d0f1e1150989b9924679b441f3404d48",
|
||||
"info_dict": {
|
||||
"id": "manofsteel-trailer",
|
||||
"ext": "mov",
|
||||
"duration": 148,
|
||||
"title": "Trailer",
|
||||
"upload_date": "20121212",
|
||||
@@ -46,15 +48,16 @@ class AppleTrailersIE(InfoExtractor):
|
||||
},
|
||||
},
|
||||
{
|
||||
"file": "manofsteel-teaser.mov",
|
||||
"md5": "5fe08795b943eb2e757fa95cb6def1cb",
|
||||
"info_dict": {
|
||||
"id": "manofsteel-teaser",
|
||||
"ext": "mov",
|
||||
"duration": 93,
|
||||
"title": "Teaser",
|
||||
"upload_date": "20120721",
|
||||
"uploader_id": "wb",
|
||||
},
|
||||
}
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
@@ -65,16 +68,16 @@ class AppleTrailersIE(InfoExtractor):
|
||||
movie = mobj.group('movie')
|
||||
uploader_id = mobj.group('company')
|
||||
|
||||
playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
|
||||
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
|
||||
def fix_html(s):
|
||||
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s)
|
||||
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
|
||||
s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
|
||||
# The ' in the onClick attributes are not escaped, it couldn't be parsed
|
||||
# like: http://trailers.apple.com/trailers/wb/gravity/
|
||||
def _clean_json(m):
|
||||
return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''')
|
||||
return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''')
|
||||
s = re.sub(self._JSON_RE, _clean_json, s)
|
||||
s = u'<html>' + s + u'</html>'
|
||||
s = '<html>' + s + u'</html>'
|
||||
return s
|
||||
doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
|
||||
|
||||
@@ -82,7 +85,7 @@ class AppleTrailersIE(InfoExtractor):
|
||||
for li in doc.findall('./div/ul/li'):
|
||||
on_click = li.find('.//a').attrib['onClick']
|
||||
trailer_info_json = self._search_regex(self._JSON_RE,
|
||||
on_click, u'trailer info')
|
||||
on_click, 'trailer info')
|
||||
trailer_info = json.loads(trailer_info_json)
|
||||
title = trailer_info['title']
|
||||
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
|
||||
@@ -98,8 +101,7 @@ class AppleTrailersIE(InfoExtractor):
|
||||
first_url = trailer_info['url']
|
||||
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
|
||||
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
|
||||
settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json')
|
||||
settings = json.loads(settings_json)
|
||||
settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
|
||||
|
||||
formats = []
|
||||
for format in settings['metadata']['sizes']:
|
||||
@@ -107,7 +109,6 @@ class AppleTrailersIE(InfoExtractor):
|
||||
format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'ext': determine_ext(format_url),
|
||||
'format': format['type'],
|
||||
'width': format['width'],
|
||||
'height': int(format['height']),
|
||||
|
@@ -1,22 +1,21 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .ooyala import OoyalaIE
|
||||
|
||||
|
||||
class BloombergIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
|
||||
u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4',
|
||||
u'info_dict': {
|
||||
u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies',
|
||||
u'description': u'md5:abc86e5236f9f0e4866c59ad36736686',
|
||||
},
|
||||
u'params': {
|
||||
# Requires ffmpeg (m3u8 manifest)
|
||||
u'skip_download': True,
|
||||
'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
|
||||
'md5': '7bf08858ff7c203c870e8a6190e221e5',
|
||||
'info_dict': {
|
||||
'id': 'qurhIVlJSB6hzkVi229d8g',
|
||||
'ext': 'flv',
|
||||
'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
|
||||
'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
|
||||
},
|
||||
}
|
||||
|
||||
@@ -24,7 +23,16 @@ class BloombergIE(InfoExtractor):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
name = mobj.group('name')
|
||||
webpage = self._download_webpage(url, name)
|
||||
embed_code = self._search_regex(
|
||||
r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage,
|
||||
'embed code')
|
||||
return OoyalaIE._build_url_result(embed_code)
|
||||
f4m_url = self._search_regex(
|
||||
r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
|
||||
'f4m url')
|
||||
title = re.sub(': Video$', '', self._og_search_title(webpage))
|
||||
|
||||
return {
|
||||
'id': name.split('-')[-1],
|
||||
'title': title,
|
||||
'url': f4m_url,
|
||||
'ext': 'flv',
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
}
|
||||
|
@@ -87,7 +87,7 @@ class BrightcoveIE(InfoExtractor):
|
||||
object_str = object_str.replace('<--', '<!--')
|
||||
object_str = fix_xml_ampersands(object_str)
|
||||
|
||||
object_doc = xml.etree.ElementTree.fromstring(object_str)
|
||||
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
|
||||
|
||||
fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
|
||||
if fv_el is not None:
|
||||
|
@@ -2,39 +2,46 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class C56IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
|
||||
_VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
|
||||
IE_NAME = '56.com'
|
||||
_TEST = {
|
||||
'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
|
||||
'file': '93440716.flv',
|
||||
'md5': 'e59995ac63d0457783ea05f93f12a866',
|
||||
'info_dict': {
|
||||
'id': '93440716',
|
||||
'ext': 'flv',
|
||||
'title': '网事知多少 第32期:车怒',
|
||||
'duration': 283.813,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
|
||||
text_id = mobj.group('textid')
|
||||
info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
|
||||
text_id, 'Downloading video info')
|
||||
info = json.loads(info_page)['info']
|
||||
formats = [{
|
||||
'format_id': f['type'],
|
||||
'filesize': int(f['filesize']),
|
||||
'url': f['url']
|
||||
} for f in info['rfiles']]
|
||||
|
||||
page = self._download_json(
|
||||
'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
|
||||
|
||||
info = page['info']
|
||||
|
||||
formats = [
|
||||
{
|
||||
'format_id': f['type'],
|
||||
'filesize': int(f['filesize']),
|
||||
'url': f['url']
|
||||
} for f in info['rfiles']
|
||||
]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': info['vid'],
|
||||
'title': info['Subject'],
|
||||
'duration': int(info['duration']) / 1000.0,
|
||||
'formats': formats,
|
||||
'thumbnail': info.get('bimg') or info.get('img'),
|
||||
}
|
||||
|
@@ -28,7 +28,7 @@ class CanalplusIE(InfoExtractor):
|
||||
video_id = mobj.groupdict().get('id')
|
||||
if video_id is None:
|
||||
webpage = self._download_webpage(url, mobj.group('path'))
|
||||
video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
|
||||
video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, u'video id')
|
||||
info_url = self._VIDEO_INFO_TEMPLATE % video_id
|
||||
doc = self._download_xml(info_url,video_id,
|
||||
u'Downloading video info')
|
||||
|
75
youtube_dl/extractor/cnet.py
Normal file
75
youtube_dl/extractor/cnet.py
Normal file
@@ -0,0 +1,75 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class CNETIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
|
||||
_TEST = {
|
||||
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
|
||||
'md5': '041233212a0d06b179c87cbcca1577b8',
|
||||
'info_dict': {
|
||||
'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hands-on with Microsoft Windows 8.1 Update',
|
||||
'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
|
||||
'thumbnail': 're:^http://.*/flmswindows8.jpg$',
|
||||
'uploader_id': 'sarah.mitroff@cbsinteractive.com',
|
||||
'uploader': 'Sarah Mitroff',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
data_json = self._html_search_regex(
|
||||
r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'",
|
||||
webpage, 'data json')
|
||||
data = json.loads(data_json)
|
||||
vdata = data['video']
|
||||
if not vdata:
|
||||
vdata = data['videos'][0]
|
||||
if not vdata:
|
||||
raise ExtractorError('Cannot find video data')
|
||||
|
||||
video_id = vdata['id']
|
||||
title = vdata['headline']
|
||||
description = vdata.get('dek')
|
||||
thumbnail = vdata.get('image', {}).get('path')
|
||||
author = vdata.get('author')
|
||||
if author:
|
||||
uploader = '%s %s' % (author['firstName'], author['lastName'])
|
||||
uploader_id = author.get('email')
|
||||
else:
|
||||
uploader = None
|
||||
uploader_id = None
|
||||
|
||||
formats = [{
|
||||
'format_id': '%s-%s-%s' % (
|
||||
f['type'], f['format'],
|
||||
int_or_none(f.get('bitrate'), 1000, default='')),
|
||||
'url': f['uri'],
|
||||
'tbr': int_or_none(f.get('bitrate'), 1000),
|
||||
} for f in vdata['files']['data']]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'description': description,
|
||||
'uploader': uploader,
|
||||
'uploader_id': uploader_id,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
@@ -8,7 +8,7 @@ from ..utils import (
|
||||
compat_str,
|
||||
compat_urllib_parse,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
@@ -41,13 +41,15 @@ class ComedyCentralShowsIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|
||||
|https?://(:www\.)?
|
||||
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
|
||||
(full-episodes/(?P<episode>.*)|
|
||||
(full-episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
|
||||
(?P<clip>
|
||||
(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|
||||
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
|
||||
(?:(?:guests/[^/]+|videos)/[^/]+/(?P<videotitle>[^/?#]+))
|
||||
|(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|
||||
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
|
||||
)|
|
||||
(?P<interview>
|
||||
extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
|
||||
$'''
|
||||
(?:[?#].*|$)'''
|
||||
_TEST = {
|
||||
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
|
||||
'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
|
||||
@@ -57,7 +59,7 @@ class ComedyCentralShowsIE(InfoExtractor):
|
||||
'upload_date': '20121213',
|
||||
'description': 'Kristen Stewart learns to let loose in "On the Road."',
|
||||
'uploader': 'thedailyshow',
|
||||
'title': 'thedailyshow-kristen-stewart part 1',
|
||||
'title': 'thedailyshow kristen-stewart part 1',
|
||||
}
|
||||
}
|
||||
|
||||
@@ -102,7 +104,9 @@ class ComedyCentralShowsIE(InfoExtractor):
|
||||
assert mobj is not None
|
||||
|
||||
if mobj.group('clip'):
|
||||
if mobj.group('showname') == 'thedailyshow':
|
||||
if mobj.group('videotitle'):
|
||||
epTitle = mobj.group('videotitle')
|
||||
elif mobj.group('showname') == 'thedailyshow':
|
||||
epTitle = mobj.group('tdstitle')
|
||||
else:
|
||||
epTitle = mobj.group('cntitle')
|
||||
@@ -159,9 +163,9 @@ class ComedyCentralShowsIE(InfoExtractor):
|
||||
thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
|
||||
|
||||
content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
|
||||
duration = int_or_none(content.attrib.get('duration'))
|
||||
duration = float_or_none(content.attrib.get('duration'))
|
||||
mediagen_url = content.attrib['url']
|
||||
guid = itemEl.find('.//guid').text.rpartition(':')[-1]
|
||||
guid = itemEl.find('./guid').text.rpartition(':')[-1]
|
||||
|
||||
cdoc = self._download_xml(
|
||||
mediagen_url, epTitle,
|
||||
|
@@ -252,6 +252,17 @@ class InfoExtractor(object):
|
||||
outf.write(webpage_bytes)
|
||||
|
||||
content = webpage_bytes.decode(encoding, 'replace')
|
||||
|
||||
if (u'<title>Access to this site is blocked</title>' in content and
|
||||
u'Websense' in content[:512]):
|
||||
msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
|
||||
blocked_iframe = self._html_search_regex(
|
||||
r'<iframe src="([^"]+)"', content,
|
||||
u'Websense information URL', default=None)
|
||||
if blocked_iframe:
|
||||
msg += u' Visit %s for more details' % blocked_iframe
|
||||
raise ExtractorError(msg, expected=True)
|
||||
|
||||
return (content, urlh)
|
||||
|
||||
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
|
||||
|
@@ -4,6 +4,7 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unescapeHTML,
|
||||
find_xpath_attr,
|
||||
)
|
||||
@@ -54,18 +55,29 @@ class CSpanIE(InfoExtractor):
|
||||
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
|
||||
data = self._download_json(info_url, video_id)
|
||||
|
||||
url = unescapeHTML(data['video']['files'][0]['path']['#text'])
|
||||
|
||||
doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
|
||||
doc = self._download_xml(
|
||||
'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
|
||||
video_id)
|
||||
|
||||
def find_string(s):
|
||||
return find_xpath_attr(doc, './/string', 'name', s).text
|
||||
title = find_xpath_attr(doc, './/string', 'name', 'title').text
|
||||
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
|
||||
|
||||
files = data['video']['files']
|
||||
|
||||
entries = [{
|
||||
'id': '%s_%d' % (video_id, partnum + 1),
|
||||
'title': (
|
||||
title if len(files) == 1 else
|
||||
'%s part %d' % (title, partnum + 1)),
|
||||
'url': unescapeHTML(f['path']['#text']),
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': int_or_none(f.get('length', {}).get('#text')),
|
||||
} for partnum, f in enumerate(files)]
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'entries': entries,
|
||||
'title': title,
|
||||
'id': video_id,
|
||||
'title': find_string('title'),
|
||||
'url': url,
|
||||
'description': description,
|
||||
'thumbnail': find_string('poster'),
|
||||
}
|
||||
|
@@ -180,7 +180,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
|
||||
class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
|
||||
IE_NAME = u'dailymotion:playlist'
|
||||
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
|
||||
_MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
|
||||
_MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
|
||||
_PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
|
||||
|
||||
def _extract_entries(self, id):
|
||||
@@ -190,10 +190,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
|
||||
webpage = self._download_webpage(request,
|
||||
id, u'Downloading page %s' % pagenum)
|
||||
|
||||
playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage)
|
||||
video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
|
||||
video_ids.extend(re.findall(r'data-id="(.+?)"', webpage))
|
||||
|
||||
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
|
||||
if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
|
||||
break
|
||||
return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
|
||||
for video_id in orderedSet(video_ids)]
|
||||
@@ -212,8 +211,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
|
||||
|
||||
class DailymotionUserIE(DailymotionPlaylistIE):
|
||||
IE_NAME = u'dailymotion:user'
|
||||
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
|
||||
_MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
|
||||
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
|
||||
_PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@@ -10,9 +10,10 @@ class DiscoveryIE(InfoExtractor):
|
||||
_VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
|
||||
_TEST = {
|
||||
'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
|
||||
'file': '614784.mp4',
|
||||
'md5': 'e12614f9ee303a6ccef415cb0793eba2',
|
||||
'info_dict': {
|
||||
'id': '614784',
|
||||
'ext': 'mp4',
|
||||
'title': 'MythBusters: Mission Impossible Outtakes',
|
||||
'description': ('Watch Jamie Hyneman and Adam Savage practice being'
|
||||
' each other -- to the point of confusing Jamie\'s dog -- and '
|
||||
@@ -34,7 +35,7 @@ class DiscoveryIE(InfoExtractor):
|
||||
formats = []
|
||||
for f in info['mp4']:
|
||||
formats.append(
|
||||
{'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])})
|
||||
{'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
|
||||
|
||||
return {
|
||||
'id': info['contentId'],
|
||||
|
@@ -1,23 +1,25 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from ..utils import (
|
||||
compat_urllib_parse,
|
||||
determine_ext
|
||||
)
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class EHowIE(InfoExtractor):
|
||||
IE_NAME = u'eHow'
|
||||
_VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
|
||||
IE_NAME = 'eHow'
|
||||
_VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
|
||||
u'file': u'12245069.flv',
|
||||
u'md5': u'9809b4e3f115ae2088440bcb4efbf371',
|
||||
u'info_dict': {
|
||||
u"title": u"Hardwood Flooring Basics",
|
||||
u"description": u"Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...",
|
||||
u"uploader": u"Erick Nathan"
|
||||
'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
|
||||
'md5': '9809b4e3f115ae2088440bcb4efbf371',
|
||||
'info_dict': {
|
||||
'id': '12245069',
|
||||
'ext': 'flv',
|
||||
'title': 'Hardwood Flooring Basics',
|
||||
'description': 'Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...',
|
||||
'uploader': 'Erick Nathan',
|
||||
}
|
||||
}
|
||||
|
||||
@@ -26,21 +28,16 @@ class EHowIE(InfoExtractor):
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
|
||||
webpage, u'video URL')
|
||||
final_url = compat_urllib_parse.unquote(video_url)
|
||||
uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
|
||||
webpage, u'uploader')
|
||||
webpage, 'video URL')
|
||||
final_url = compat_urllib_parse.unquote(video_url)
|
||||
uploader = self._html_search_meta('uploader', webpage)
|
||||
title = self._og_search_title(webpage).replace(' | eHow', '')
|
||||
ext = determine_ext(final_url)
|
||||
|
||||
return {
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'url': final_url,
|
||||
'ext': ext,
|
||||
'title': title,
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
'id': video_id,
|
||||
'url': final_url,
|
||||
'title': title,
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
'description': self._og_search_description(webpage),
|
||||
'uploader': uploader,
|
||||
'uploader': uploader,
|
||||
}
|
||||
|
||||
|
77
youtube_dl/extractor/franceculture.py
Normal file
77
youtube_dl/extractor/franceculture.py
Normal file
@@ -0,0 +1,77 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_parse_qs,
|
||||
compat_urlparse,
|
||||
)
|
||||
|
||||
|
||||
class FranceCultureIE(InfoExtractor):
|
||||
_VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
|
||||
'info_dict': {
|
||||
'id': '4795174',
|
||||
'ext': 'mp3',
|
||||
'title': 'Rendez-vous au pays des geeks',
|
||||
'vcodec': 'none',
|
||||
'uploader': 'Colette Fellous',
|
||||
'upload_date': '20140301',
|
||||
'duration': 3601,
|
||||
'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
|
||||
'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
baseurl = mobj.group('baseurl')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
params_code = self._search_regex(
|
||||
r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />",
|
||||
webpage, 'parameter code')
|
||||
params = compat_parse_qs(params_code)
|
||||
video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0])
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title')
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
|
||||
webpage, 'uploader', fatal=False)
|
||||
thumbnail_part = self._html_search_regex(
|
||||
r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage,
|
||||
'thumbnail', fatal=False)
|
||||
if thumbnail_part is None:
|
||||
thumbnail = None
|
||||
else:
|
||||
thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part)
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<p class="desc">(.*?)</p>', webpage, 'description')
|
||||
|
||||
info = json.loads(params['infoData'][0])[0]
|
||||
duration = info.get('media_length')
|
||||
upload_date_candidate = info.get('media_section5')
|
||||
upload_date = (
|
||||
upload_date_candidate
|
||||
if (upload_date_candidate is not None and
|
||||
re.match(r'[0-9]{8}$', upload_date_candidate))
|
||||
else None)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'vcodec': 'none' if video_url.lower().endswith('.mp3') else None,
|
||||
'duration': duration,
|
||||
'uploader': uploader,
|
||||
'upload_date': upload_date,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'description': description,
|
||||
}
|
@@ -25,6 +25,7 @@ from ..utils import (
|
||||
from .brightcove import BrightcoveIE
|
||||
from .ooyala import OoyalaIE
|
||||
from .rutv import RUTVIE
|
||||
from .smotri import SmotriIE
|
||||
|
||||
|
||||
class GenericIE(InfoExtractor):
|
||||
@@ -81,6 +82,17 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
'add_ie': ['Brightcove'],
|
||||
},
|
||||
{
|
||||
'url': 'http://www.championat.com/video/football/v/87/87499.html',
|
||||
'md5': 'fb973ecf6e4a78a67453647444222983',
|
||||
'info_dict': {
|
||||
'id': '3414141473001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Видео. Удаление Дзагоева (ЦСКА)',
|
||||
'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
|
||||
'uploader': 'Championat',
|
||||
},
|
||||
},
|
||||
# Direct link to a video
|
||||
{
|
||||
'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
|
||||
@@ -102,20 +114,6 @@ class GenericIE(InfoExtractor):
|
||||
'title': '2cc213299525360.mov', # that's what we get
|
||||
},
|
||||
},
|
||||
# second style of embedded ooyala videos
|
||||
{
|
||||
'url': 'http://www.smh.com.au/tv/business/show/financial-review-sunday/behind-the-scenes-financial-review-sunday--4350201.html',
|
||||
'info_dict': {
|
||||
'id': '13djJjYjptA1XpPx8r9kuzPyj3UZH0Uk',
|
||||
'ext': 'mp4',
|
||||
'title': 'Behind-the-scenes: Financial Review Sunday ',
|
||||
'description': 'Step inside Channel Nine studios for an exclusive tour of its upcoming financial business show.',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
# google redirect
|
||||
{
|
||||
'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
|
||||
@@ -212,6 +210,21 @@ class GenericIE(InfoExtractor):
|
||||
'skip_download': 'Requires rtmpdump'
|
||||
}
|
||||
},
|
||||
# smotri embed
|
||||
{
|
||||
'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml',
|
||||
'md5': 'ec40048448e9284c9a1de77bb188108b',
|
||||
'info_dict': {
|
||||
'id': 'v27008541fad',
|
||||
'ext': 'mp4',
|
||||
'title': 'Крым и Севастополь вошли в состав России',
|
||||
'description': 'md5:fae01b61f68984c7bd2fa741e11c3175',
|
||||
'duration': 900,
|
||||
'upload_date': '20140318',
|
||||
'uploader': 'rbctv_2012_4',
|
||||
'uploader_id': 'rbctv_2012_4',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def report_download_webpage(self, video_id):
|
||||
@@ -300,13 +313,16 @@ class GenericIE(InfoExtractor):
|
||||
if not parsed_url.scheme:
|
||||
default_search = self._downloader.params.get('default_search')
|
||||
if default_search is None:
|
||||
default_search = 'auto'
|
||||
default_search = 'auto_warning'
|
||||
|
||||
if default_search == 'auto':
|
||||
if default_search in ('auto', 'auto_warning'):
|
||||
if '/' in url:
|
||||
self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
|
||||
return self.url_result('http://' + url)
|
||||
else:
|
||||
if default_search == 'auto_warning':
|
||||
self._downloader.report_warning(
|
||||
'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url)
|
||||
return self.url_result('ytsearch:' + url)
|
||||
else:
|
||||
assert ':' in default_search
|
||||
@@ -547,6 +563,11 @@ class GenericIE(InfoExtractor):
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
|
||||
|
||||
# Look for embedded smotri.com player
|
||||
smotri_url = SmotriIE._extract_url(webpage)
|
||||
if smotri_url:
|
||||
return self.url_result(smotri_url, 'Smotri')
|
||||
|
||||
# Start with something easy: JW Player in SWFObject
|
||||
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
|
||||
if mobj is None:
|
||||
|
@@ -21,9 +21,10 @@ class HuffPostIE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677',
|
||||
'file': '52dd3e4b02a7602131000677.mp4',
|
||||
'md5': '55f5e8981c1c80a64706a44b74833de8',
|
||||
'info_dict': {
|
||||
'id': '52dd3e4b02a7602131000677',
|
||||
'ext': 'mp4',
|
||||
'title': 'Legalese It! with @MikeSacksHP',
|
||||
'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more. ',
|
||||
'duration': 1549,
|
||||
|
@@ -1,10 +1,8 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
|
||||
class IGNIE(InfoExtractor):
|
||||
@@ -14,52 +12,57 @@ class IGNIE(InfoExtractor):
|
||||
"""
|
||||
|
||||
_VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)'
|
||||
IE_NAME = u'ign.com'
|
||||
IE_NAME = 'ign.com'
|
||||
|
||||
_CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
|
||||
_DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>',
|
||||
r'id="my_show_video">.*?<p>(.*?)</p>',
|
||||
]
|
||||
_DESCRIPTION_RE = [
|
||||
r'<span class="page-object-description">(.+?)</span>',
|
||||
r'id="my_show_video">.*?<p>(.*?)</p>',
|
||||
]
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
|
||||
u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
|
||||
u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
|
||||
u'info_dict': {
|
||||
u'title': u'The Last of Us Review',
|
||||
u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
|
||||
'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
|
||||
'md5': 'eac8bdc1890980122c3b66f14bdd02e9',
|
||||
'info_dict': {
|
||||
'id': '8f862beef863986b2785559b9e1aa599',
|
||||
'ext': 'mp4',
|
||||
'title': 'The Last of Us Review',
|
||||
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
|
||||
}
|
||||
},
|
||||
{
|
||||
u'url': u'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
|
||||
u'playlist': [
|
||||
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
|
||||
'playlist': [
|
||||
{
|
||||
u'file': u'5ebbd138523268b93c9141af17bec937.mp4',
|
||||
u'info_dict': {
|
||||
u'title': u'GTA 5 Video Review',
|
||||
u'description': u'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
|
||||
'info_dict': {
|
||||
'id': '5ebbd138523268b93c9141af17bec937',
|
||||
'ext': 'mp4',
|
||||
'title': 'GTA 5 Video Review',
|
||||
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
|
||||
},
|
||||
},
|
||||
{
|
||||
u'file': u'638672ee848ae4ff108df2a296418ee2.mp4',
|
||||
u'info_dict': {
|
||||
u'title': u'26 Twisted Moments from GTA 5 in Slow Motion',
|
||||
u'description': u'The twisted beauty of GTA 5 in stunning slow motion.',
|
||||
'info_dict': {
|
||||
'id': '638672ee848ae4ff108df2a296418ee2',
|
||||
'ext': 'mp4',
|
||||
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
|
||||
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
|
||||
},
|
||||
},
|
||||
],
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _find_video_id(self, webpage):
|
||||
res_id = [r'data-video-id="(.+?)"',
|
||||
r'<object id="vid_(.+?)"',
|
||||
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
|
||||
]
|
||||
res_id = [
|
||||
r'data-video-id="(.+?)"',
|
||||
r'<object id="vid_(.+?)"',
|
||||
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
|
||||
]
|
||||
return self._search_regex(res_id, webpage, 'video id')
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -68,7 +71,7 @@ class IGNIE(InfoExtractor):
|
||||
page_type = mobj.group('type')
|
||||
webpage = self._download_webpage(url, name_or_id)
|
||||
if page_type == 'articles':
|
||||
video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
|
||||
video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
|
||||
return self.url_result(video_url, ie='IGN')
|
||||
elif page_type != 'video':
|
||||
multiple_urls = re.findall(
|
||||
@@ -80,41 +83,37 @@ class IGNIE(InfoExtractor):
|
||||
video_id = self._find_video_id(webpage)
|
||||
result = self._get_video_info(video_id)
|
||||
description = self._html_search_regex(self._DESCRIPTION_RE,
|
||||
webpage, 'video description',
|
||||
flags=re.DOTALL)
|
||||
webpage, 'video description', flags=re.DOTALL)
|
||||
result['description'] = description
|
||||
return result
|
||||
|
||||
def _get_video_info(self, video_id):
|
||||
config_url = self._CONFIG_URL_TEMPLATE % video_id
|
||||
config = json.loads(self._download_webpage(config_url, video_id,
|
||||
u'Downloading video info'))
|
||||
config = self._download_json(config_url, video_id)
|
||||
media = config['playlist']['media']
|
||||
video_url = media['url']
|
||||
|
||||
return {'id': media['metadata']['videoId'],
|
||||
'url': video_url,
|
||||
'ext': determine_ext(video_url),
|
||||
'title': media['metadata']['title'],
|
||||
'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
|
||||
}
|
||||
return {
|
||||
'id': media['metadata']['videoId'],
|
||||
'url': media['url'],
|
||||
'title': media['metadata']['title'],
|
||||
'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
|
||||
}
|
||||
|
||||
|
||||
class OneUPIE(IGNIE):
|
||||
"""Extractor for 1up.com, it uses the ign videos system."""
|
||||
|
||||
_VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
|
||||
IE_NAME = '1up.com'
|
||||
|
||||
_DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://gamevideos.1up.com/video/id/34976',
|
||||
u'file': u'34976.mp4',
|
||||
u'md5': u'68a54ce4ebc772e4b71e3123d413163d',
|
||||
u'info_dict': {
|
||||
u'title': u'Sniper Elite V2 - Trailer',
|
||||
u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf',
|
||||
'url': 'http://gamevideos.1up.com/video/id/34976',
|
||||
'md5': '68a54ce4ebc772e4b71e3123d413163d',
|
||||
'info_dict': {
|
||||
'id': '34976',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sniper Elite V2 - Trailer',
|
||||
'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf',
|
||||
}
|
||||
}
|
||||
|
||||
@@ -123,7 +122,6 @@ class OneUPIE(IGNIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
id = mobj.group('name_or_id')
|
||||
result = super(OneUPIE, self)._real_extract(url)
|
||||
result['id'] = id
|
||||
result['id'] = mobj.group('name_or_id')
|
||||
return result
|
||||
|
@@ -1,37 +1,39 @@
|
||||
# encoding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class KickStarterIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*'
|
||||
_VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
|
||||
_TEST = {
|
||||
u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location",
|
||||
u"file": u"1404461844.mp4",
|
||||
u"md5": u"c81addca81327ffa66c642b5d8b08cab",
|
||||
u"info_dict": {
|
||||
u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling",
|
||||
'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location',
|
||||
'md5': 'c81addca81327ffa66c642b5d8b08cab',
|
||||
'info_dict': {
|
||||
'id': '1404461844',
|
||||
'ext': 'mp4',
|
||||
'title': 'Intersection: The Story of Josh Grant by Kyle Cowling',
|
||||
'description': 'A unique motocross documentary that examines the '
|
||||
'life and mind of one of sports most elite athletes: Josh Grant.',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
m = re.match(self._VALID_URL, url)
|
||||
video_id = m.group('id')
|
||||
webpage_src = self._download_webpage(url, video_id)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = self._search_regex(r'data-video="(.*?)">',
|
||||
webpage_src, u'video URL')
|
||||
if 'mp4' in video_url:
|
||||
ext = 'mp4'
|
||||
else:
|
||||
ext = 'flv'
|
||||
video_title = self._html_search_regex(r"<title>(.*?)</title>",
|
||||
webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip()
|
||||
video_url = self._search_regex(r'data-video-url="(.*?)"',
|
||||
webpage, 'video URL')
|
||||
video_title = self._html_search_regex(r'<title>(.*?)</title>',
|
||||
webpage, 'title').rpartition('— Kickstarter')[0].strip()
|
||||
|
||||
results = [{
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': video_title,
|
||||
'ext': ext,
|
||||
}]
|
||||
return results
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': video_title,
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
}
|
||||
|
@@ -13,8 +13,9 @@ class MetacriticIE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',
|
||||
'file': '3698222.mp4',
|
||||
'info_dict': {
|
||||
'id': '3698222',
|
||||
'ext': 'mp4',
|
||||
'title': 'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors',
|
||||
'description': 'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.',
|
||||
'duration': 221,
|
||||
|
@@ -14,7 +14,7 @@ from ..utils import (
|
||||
class MooshareIE(InfoExtractor):
|
||||
IE_NAME = 'mooshare'
|
||||
IE_DESC = 'Mooshare.biz'
|
||||
_VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})'
|
||||
_VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
|
55
youtube_dl/extractor/morningstar.py
Normal file
55
youtube_dl/extractor/morningstar.py
Normal file
@@ -0,0 +1,55 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class MorningstarIE(InfoExtractor):
|
||||
IE_DESC = 'morningstar.com'
|
||||
_VALID_URL = r'https?://(?:www\.)?morningstar\.com/cover/videocenter\.aspx\?id=(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869',
|
||||
'md5': '6c0acface7a787aadc8391e4bbf7b0f5',
|
||||
'info_dict': {
|
||||
'id': '615869',
|
||||
'ext': 'mp4',
|
||||
'title': 'Get Ahead of the Curve on 2013 Taxes',
|
||||
'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.",
|
||||
'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_regex(
|
||||
r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title')
|
||||
video_url = self._html_search_regex(
|
||||
r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"',
|
||||
webpage, 'video URL')
|
||||
thumbnail = self._html_search_regex(
|
||||
r'<input type="hidden" id="hidSnapshot" value="([^"]+)"',
|
||||
webpage, 'thumbnail', fatal=False)
|
||||
description = self._html_search_regex(
|
||||
r'<div id="mstarDeck".*?>(.*?)</div>',
|
||||
webpage, 'description', fatal=False)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': video_url,
|
||||
'thumbnail': thumbnail,
|
||||
'description': description,
|
||||
}
|
63
youtube_dl/extractor/motorsport.py
Normal file
63
youtube_dl/extractor/motorsport.py
Normal file
@@ -0,0 +1,63 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class MotorsportIE(InfoExtractor):
|
||||
IE_DESC = 'motorsport.com'
|
||||
_VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
|
||||
_TEST = {
|
||||
'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
|
||||
'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
|
||||
'info_dict': {
|
||||
'id': '7063',
|
||||
'ext': 'mp4',
|
||||
'title': 'Red Bull Racing: 2014 Rules Explained',
|
||||
'duration': 207,
|
||||
'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
|
||||
'uploader': 'rainiere',
|
||||
'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
flashvars_code = self._html_search_regex(
|
||||
r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
|
||||
flashvars = compat_parse_qs(flashvars_code)
|
||||
params = json.loads(flashvars['parameters'][0])
|
||||
|
||||
e = compat_str(int(time.time()) + 24 * 60 * 60)
|
||||
base_video_url = params['location'] + '?e=' + e
|
||||
s = 'h3hg713fh32'
|
||||
h = hashlib.md5(s + base_video_url).hexdigest()
|
||||
video_url = base_video_url + '&h=' + h
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
|
||||
'uploader', fatal=False)
|
||||
|
||||
return {
|
||||
'id': params['video_id'],
|
||||
'display_id': display_id,
|
||||
'title': params['title'],
|
||||
'url': video_url,
|
||||
'description': params.get('description'),
|
||||
'thumbnail': params.get('main_thumb'),
|
||||
'duration': int_or_none(params.get('duration')),
|
||||
'uploader': uploader,
|
||||
}
|
75
youtube_dl/extractor/musicplayon.py
Normal file
75
youtube_dl/extractor/musicplayon.py
Normal file
@@ -0,0 +1,75 @@
|
||||
# encoding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class MusicPlayOnIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=100&play)=(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://en.musicplayon.com/play?v=433377',
|
||||
'info_dict': {
|
||||
'id': '433377',
|
||||
'ext': 'mp4',
|
||||
'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
|
||||
'description': 'Rick Ross Interview On Chelsea Lately',
|
||||
'duration': 342,
|
||||
'uploader': 'ultrafish',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
page = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._og_search_title(page)
|
||||
description = self._og_search_description(page)
|
||||
thumbnail = self._og_search_thumbnail(page)
|
||||
duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
|
||||
view_count = self._og_search_property('count', page, fatal=False)
|
||||
uploader = self._html_search_regex(
|
||||
r'<div>by <a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
|
||||
|
||||
formats = [
|
||||
{
|
||||
'url': 'http://media0-eu-nl.musicplayon.com/stream-mobile?id=%s&type=.mp4' % video_id,
|
||||
'ext': 'mp4',
|
||||
}
|
||||
]
|
||||
|
||||
manifest = self._download_webpage(
|
||||
'http://en.musicplayon.com/manifest.m3u8?v=%s' % video_id, video_id, 'Downloading manifest')
|
||||
|
||||
for entry in manifest.split('#')[1:]:
|
||||
if entry.startswith('EXT-X-STREAM-INF:'):
|
||||
meta, url, _ = entry.split('\n')
|
||||
params = dict(param.split('=') for param in meta.split(',')[1:])
|
||||
formats.append({
|
||||
'url': url,
|
||||
'ext': 'mp4',
|
||||
'tbr': int(params['BANDWIDTH']),
|
||||
'width': int(params['RESOLUTION'].split('x')[1]),
|
||||
'height': int(params['RESOLUTION'].split('x')[-1]),
|
||||
'format_note': params['NAME'].replace('"', '').strip(),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'duration': int_or_none(duration),
|
||||
'view_count': int_or_none(view_count),
|
||||
'formats': formats,
|
||||
}
|
@@ -6,12 +6,13 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class NBAIE(InfoExtractor):
|
||||
_VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
|
||||
_VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
|
||||
_TEST = {
|
||||
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
|
||||
'file': u'0021200253-okc-bkn-recap.nba.mp4',
|
||||
'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
|
||||
'info_dict': {
|
||||
'id': '0021200253-okc-bkn-recap.nba',
|
||||
'ext': 'mp4',
|
||||
'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
|
||||
'title': 'Thunder vs. Nets',
|
||||
},
|
||||
@@ -19,7 +20,7 @@ class NBAIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group(1)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
@@ -33,7 +34,6 @@ class NBAIE(InfoExtractor):
|
||||
return {
|
||||
'id': shortened_video_id,
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'title': title,
|
||||
'description': description,
|
||||
}
|
||||
|
@@ -1,12 +1,10 @@
|
||||
# encoding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import socket
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_http_client,
|
||||
compat_urllib_error,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
@@ -18,57 +16,54 @@ from ..utils import (
|
||||
|
||||
|
||||
class NiconicoIE(InfoExtractor):
|
||||
IE_NAME = u'niconico'
|
||||
IE_DESC = u'ニコニコ動画'
|
||||
IE_NAME = 'niconico'
|
||||
IE_DESC = 'ニコニコ動画'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.nicovideo.jp/watch/sm22312215',
|
||||
u'file': u'sm22312215.mp4',
|
||||
u'md5': u'd1a75c0823e2f629128c43e1212760f9',
|
||||
u'info_dict': {
|
||||
u'title': u'Big Buck Bunny',
|
||||
u'uploader': u'takuya0301',
|
||||
u'uploader_id': u'2698420',
|
||||
u'upload_date': u'20131123',
|
||||
u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
||||
'url': 'http://www.nicovideo.jp/watch/sm22312215',
|
||||
'md5': 'd1a75c0823e2f629128c43e1212760f9',
|
||||
'info_dict': {
|
||||
'id': 'sm22312215',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny',
|
||||
'uploader': 'takuya0301',
|
||||
'uploader_id': '2698420',
|
||||
'upload_date': '20131123',
|
||||
'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
|
||||
},
|
||||
u'params': {
|
||||
u'username': u'ydl.niconico@gmail.com',
|
||||
u'password': u'youtube-dl',
|
||||
'params': {
|
||||
'username': 'ydl.niconico@gmail.com',
|
||||
'password': 'youtube-dl',
|
||||
},
|
||||
}
|
||||
|
||||
_VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
|
||||
_NETRC_MACHINE = 'niconico'
|
||||
# If True it will raise an error if no login info is provided
|
||||
_LOGIN_REQUIRED = True
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
def _login(self):
|
||||
(username, password) = self._get_login_info()
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
if self._LOGIN_REQUIRED:
|
||||
raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
|
||||
return False
|
||||
# Login is required
|
||||
raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
|
||||
|
||||
# Log in
|
||||
login_form_strs = {
|
||||
u'mail': username,
|
||||
u'password': password,
|
||||
'mail': username,
|
||||
'password': password,
|
||||
}
|
||||
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
|
||||
# chokes on unicode
|
||||
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
|
||||
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
|
||||
login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
|
||||
request = compat_urllib_request.Request(
|
||||
u'https://secure.nicovideo.jp/secure/login', login_data)
|
||||
'https://secure.nicovideo.jp/secure/login', login_data)
|
||||
login_results = self._download_webpage(
|
||||
request, u'', note=u'Logging in', errnote=u'Unable to log in')
|
||||
request, None, note='Logging in', errnote='Unable to log in')
|
||||
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
|
||||
self._downloader.report_warning(u'unable to log in: bad username or password')
|
||||
self._downloader.report_warning('unable to log in: bad username or password')
|
||||
return False
|
||||
return True
|
||||
|
||||
@@ -82,12 +77,12 @@ class NiconicoIE(InfoExtractor):
|
||||
|
||||
video_info = self._download_xml(
|
||||
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
|
||||
note=u'Downloading video info page')
|
||||
note='Downloading video info page')
|
||||
|
||||
# Get flv info
|
||||
flv_info_webpage = self._download_webpage(
|
||||
u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
|
||||
video_id, u'Downloading flv info')
|
||||
'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
|
||||
video_id, 'Downloading flv info')
|
||||
video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
|
||||
|
||||
# Start extracting information
|
||||
@@ -106,22 +101,22 @@ class NiconicoIE(InfoExtractor):
|
||||
url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
|
||||
try:
|
||||
user_info = self._download_xml(
|
||||
url, video_id, note=u'Downloading user information')
|
||||
url, video_id, note='Downloading user information')
|
||||
video_uploader = user_info.find('.//nickname').text
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err))
|
||||
except ExtractorError as err:
|
||||
self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_real_url,
|
||||
'title': video_title,
|
||||
'ext': video_extension,
|
||||
'format': video_format,
|
||||
'thumbnail': video_thumbnail,
|
||||
'id': video_id,
|
||||
'url': video_real_url,
|
||||
'title': video_title,
|
||||
'ext': video_extension,
|
||||
'format': video_format,
|
||||
'thumbnail': video_thumbnail,
|
||||
'description': video_description,
|
||||
'uploader': video_uploader,
|
||||
'uploader': video_uploader,
|
||||
'upload_date': video_upload_date,
|
||||
'uploader_id': video_uploader_id,
|
||||
'view_count': video_view_count,
|
||||
'view_count': video_view_count,
|
||||
'webpage_url': video_webpage_url,
|
||||
}
|
||||
|
157
youtube_dl/extractor/ntv.py
Normal file
157
youtube_dl/extractor/ntv.py
Normal file
@@ -0,0 +1,157 @@
|
||||
# encoding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unescapeHTML
|
||||
)
|
||||
|
||||
|
||||
class NTVIE(InfoExtractor):
|
||||
_VALID_URL = r'http://(?:www\.)?ntv\.ru/(?P<id>.+)'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.ntv.ru/novosti/863142/',
|
||||
'info_dict': {
|
||||
'id': '746000',
|
||||
'ext': 'flv',
|
||||
'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
|
||||
'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
|
||||
'duration': 136,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.ntv.ru/video/novosti/750370/',
|
||||
'info_dict': {
|
||||
'id': '750370',
|
||||
'ext': 'flv',
|
||||
'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
|
||||
'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
|
||||
'duration': 172,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
|
||||
'info_dict': {
|
||||
'id': '747480',
|
||||
'ext': 'flv',
|
||||
'title': '«Сегодня». 21 марта 2014 года. 16:00 ',
|
||||
'description': '«Сегодня». 21 марта 2014 года. 16:00 ',
|
||||
'duration': 1496,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.ntv.ru/kino/Koma_film',
|
||||
'info_dict': {
|
||||
'id': '750783',
|
||||
'ext': 'flv',
|
||||
'title': 'Остросюжетный фильм «Кома» 4 апреля вечером на НТВ',
|
||||
'description': 'Остросюжетный фильм «Кома» 4 апреля вечером на НТВ',
|
||||
'duration': 28,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
|
||||
'info_dict': {
|
||||
'id': '751482',
|
||||
'ext': 'flv',
|
||||
'title': '«Дело врачей»: «Деревце жизни»',
|
||||
'description': '«Дело врачей»: «Деревце жизни»',
|
||||
'duration': 2590,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
_VIDEO_ID_REGEXES = [
|
||||
r'<meta property="og:url" content="http://www\.ntv\.ru/video/(\d+)',
|
||||
r'<video embed=[^>]+><id>(\d+)</id>',
|
||||
r'<video restriction[^>]+><key>(\d+)</key>'
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
page = self._download_webpage(url, video_id, 'Downloading page')
|
||||
|
||||
for pattern in self._VIDEO_ID_REGEXES:
|
||||
mobj = re.search(pattern, page)
|
||||
if mobj:
|
||||
break
|
||||
|
||||
if not mobj:
|
||||
raise ExtractorError('No media links available for %s' % video_id)
|
||||
|
||||
video_id = mobj.group(1)
|
||||
|
||||
player = self._download_xml('http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML')
|
||||
title = unescapeHTML(player.find('./data/title').text)
|
||||
description = unescapeHTML(player.find('./data/description').text)
|
||||
|
||||
video = player.find('./data/video')
|
||||
video_id = video.find('./id').text
|
||||
thumbnail = video.find('./splash').text
|
||||
duration = int(video.find('./totaltime').text)
|
||||
view_count = int(video.find('./views').text)
|
||||
puid22 = video.find('./puid22').text
|
||||
|
||||
apps = {
|
||||
'4': 'video1',
|
||||
'7': 'video2',
|
||||
}
|
||||
|
||||
app = apps[puid22] if puid22 in apps else apps['4']
|
||||
|
||||
formats = []
|
||||
for format_id in ['', 'hi', 'webm']:
|
||||
file = video.find('./%sfile' % format_id)
|
||||
if file is None:
|
||||
continue
|
||||
size = video.find('./%ssize' % format_id)
|
||||
formats.append({
|
||||
'url': 'rtmp://media.ntv.ru/%s' % app,
|
||||
'app': app,
|
||||
'play_path': file.text,
|
||||
'rtmp_conn': 'B:1',
|
||||
'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128',
|
||||
'page_url': 'http://www.ntv.ru',
|
||||
'flash_ver': 'LNX 11,2,202,341',
|
||||
'rtmp_live': True,
|
||||
'ext': 'flv',
|
||||
'filesize': int(size.text),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'formats': formats,
|
||||
}
|
40
youtube_dl/extractor/oe1.py
Normal file
40
youtube_dl/extractor/oe1.py
Normal file
@@ -0,0 +1,40 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import calendar
|
||||
import datetime
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
# audios on oe1.orf.at are only available for 7 days, so we can't
|
||||
# add tests.
|
||||
|
||||
|
||||
class OE1IE(InfoExtractor):
|
||||
IE_DESC = 'oe1.orf.at'
|
||||
_VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
show_id = mobj.group('id')
|
||||
|
||||
data = self._download_json(
|
||||
'http://oe1.orf.at/programm/%s/konsole' % show_id,
|
||||
show_id
|
||||
)
|
||||
|
||||
timestamp = datetime.datetime.strptime('%s %s' % (
|
||||
data['item']['day_label'],
|
||||
data['item']['time']
|
||||
), '%d.%m.%Y %H:%M')
|
||||
unix_timestamp = calendar.timegm(timestamp.utctimetuple())
|
||||
|
||||
return {
|
||||
'id': show_id,
|
||||
'title': data['item']['title'],
|
||||
'url': data['item']['url_stream'],
|
||||
'ext': 'mp3',
|
||||
'description': data['item'].get('info'),
|
||||
'timestamp': unix_timestamp
|
||||
}
|
@@ -1,3 +1,5 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import os
|
||||
|
||||
@@ -5,45 +7,50 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class PyvideoIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
|
||||
_TESTS = [{
|
||||
u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
|
||||
u'file': u'24_4WWkSmNo.mp4',
|
||||
u'md5': u'de317418c8bc76b1fd8633e4f32acbc6',
|
||||
u'info_dict': {
|
||||
u"title": u"Become a logging expert in 30 minutes",
|
||||
u"description": u"md5:9665350d466c67fb5b1598de379021f7",
|
||||
u"upload_date": u"20130320",
|
||||
u"uploader": u"NextDayVideo",
|
||||
u"uploader_id": u"NextDayVideo",
|
||||
_VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
|
||||
'md5': 'de317418c8bc76b1fd8633e4f32acbc6',
|
||||
'info_dict': {
|
||||
'id': '24_4WWkSmNo',
|
||||
'ext': 'mp4',
|
||||
'title': 'Become a logging expert in 30 minutes',
|
||||
'description': 'md5:9665350d466c67fb5b1598de379021f7',
|
||||
'upload_date': '20130320',
|
||||
'uploader': 'NextDayVideo',
|
||||
'uploader_id': 'NextDayVideo',
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
},
|
||||
u'add_ie': ['Youtube'],
|
||||
},
|
||||
{
|
||||
u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
|
||||
u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12',
|
||||
u'info_dict': {
|
||||
u'id': u'2542',
|
||||
u'ext': u'm4v',
|
||||
u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
|
||||
{
|
||||
'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
|
||||
'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
|
||||
'info_dict': {
|
||||
'id': '2542',
|
||||
'ext': 'm4v',
|
||||
'title': 'Gloriajw-SpotifyWithErikBernhardsson182',
|
||||
},
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
|
||||
if m_youtube is not None:
|
||||
return self.url_result(m_youtube.group(1), 'Youtube')
|
||||
|
||||
title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>',
|
||||
webpage, u'title', flags=re.DOTALL)
|
||||
video_url = self._search_regex([r'<source src="(.*?)"',
|
||||
r'<dt>Download</dt>.*?<a href="(.+?)"'],
|
||||
webpage, u'video url', flags=re.DOTALL)
|
||||
title = self._html_search_regex(
|
||||
r'<div class="section">.*?<h3>([^>]+?)</h3>', webpage, 'title', flags=re.DOTALL)
|
||||
video_url = self._search_regex(
|
||||
[r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],
|
||||
webpage, 'video url', flags=re.DOTALL)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': os.path.splitext(title)[0],
|
||||
|
@@ -1,5 +1,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import unified_strdate, determine_ext
|
||||
@@ -9,41 +10,44 @@ class RoxwelIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.roxwel.com/player/passionpittakeawalklive.html',
|
||||
u'file': u'passionpittakeawalklive.flv',
|
||||
u'md5': u'd9dea8360a1e7d485d2206db7fe13035',
|
||||
u'info_dict': {
|
||||
u'title': u'Take A Walk (live)',
|
||||
u'uploader': u'Passion Pit',
|
||||
u'description': u'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ',
|
||||
'url': 'http://www.roxwel.com/player/passionpittakeawalklive.html',
|
||||
'info_dict': {
|
||||
'id': 'passionpittakeawalklive',
|
||||
'ext': 'flv',
|
||||
'title': 'Take A Walk (live)',
|
||||
'uploader': 'Passion Pit',
|
||||
'uploader_id': 'passionpit',
|
||||
'upload_date': '20120928',
|
||||
'description': 'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ',
|
||||
},
|
||||
u'skip': u'Requires rtmpdump',
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
filename = mobj.group('filename')
|
||||
info_url = 'http://www.roxwel.com/api/videos/%s' % filename
|
||||
info_page = self._download_webpage(info_url, filename,
|
||||
u'Downloading video info')
|
||||
info = self._download_json(info_url, filename)
|
||||
|
||||
self.report_extraction(filename)
|
||||
info = json.loads(info_page)
|
||||
rtmp_rates = sorted([int(r.replace('flv_', '')) for r in info['media_rates'] if r.startswith('flv_')])
|
||||
best_rate = rtmp_rates[-1]
|
||||
url_page_url = 'http://roxwel.com/pl_one_time.php?filename=%s&quality=%s' % (filename, best_rate)
|
||||
rtmp_url = self._download_webpage(url_page_url, filename, u'Downloading video url')
|
||||
rtmp_url = self._download_webpage(url_page_url, filename, 'Downloading video url')
|
||||
ext = determine_ext(rtmp_url)
|
||||
if ext == 'f4v':
|
||||
rtmp_url = rtmp_url.replace(filename, 'mp4:%s' % filename)
|
||||
|
||||
return {'id': filename,
|
||||
'title': info['title'],
|
||||
'url': rtmp_url,
|
||||
'ext': 'flv',
|
||||
'description': info['description'],
|
||||
'thumbnail': info.get('player_image_url') or info.get('image_url_large'),
|
||||
'uploader': info['artist'],
|
||||
'uploader_id': info['artistname'],
|
||||
'upload_date': unified_strdate(info['dbdate']),
|
||||
}
|
||||
return {
|
||||
'id': filename,
|
||||
'title': info['title'],
|
||||
'url': rtmp_url,
|
||||
'ext': 'flv',
|
||||
'description': info['description'],
|
||||
'thumbnail': info.get('player_image_url') or info.get('image_url_large'),
|
||||
'uploader': info['artist'],
|
||||
'uploader_id': info['artistname'],
|
||||
'upload_date': unified_strdate(info['dbdate']),
|
||||
}
|
||||
|
@@ -2,7 +2,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
import itertools
|
||||
|
||||
from .common import InfoExtractor
|
||||
@@ -20,8 +19,9 @@ class RutubeIE(InfoExtractor):
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
|
||||
'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4',
|
||||
'info_dict': {
|
||||
'id': '3eac3b4561676c17df9132a9a1e62e3e',
|
||||
'ext': 'mp4',
|
||||
'title': 'Раненный кенгуру забежал в аптеку',
|
||||
'description': 'http://www.ntdtv.ru ',
|
||||
'duration': 80,
|
||||
@@ -38,15 +38,15 @@ class RutubeIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id,
|
||||
video_id, 'Downloading video JSON')
|
||||
video = json.loads(api_response)
|
||||
|
||||
api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
|
||||
video_id, 'Downloading trackinfo JSON')
|
||||
trackinfo = json.loads(api_response)
|
||||
|
||||
|
||||
video = self._download_json(
|
||||
'http://rutube.ru/api/video/%s/?format=json' % video_id,
|
||||
video_id, 'Downloading video JSON')
|
||||
|
||||
trackinfo = self._download_json(
|
||||
'http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
|
||||
video_id, 'Downloading trackinfo JSON')
|
||||
|
||||
# Some videos don't have the author field
|
||||
author = trackinfo.get('author') or {}
|
||||
m3u8_url = trackinfo['video_balancer'].get('m3u8')
|
||||
@@ -79,10 +79,9 @@ class RutubeChannelIE(InfoExtractor):
|
||||
def _extract_videos(self, channel_id, channel_title=None):
|
||||
entries = []
|
||||
for pagenum in itertools.count(1):
|
||||
api_response = self._download_webpage(
|
||||
page = self._download_json(
|
||||
self._PAGE_TEMPLATE % (channel_id, pagenum),
|
||||
channel_id, 'Downloading page %s' % pagenum)
|
||||
page = json.loads(api_response)
|
||||
results = page['results']
|
||||
if not results:
|
||||
break
|
||||
@@ -108,10 +107,9 @@ class RutubeMovieIE(RutubeChannelIE):
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
movie_id = mobj.group('id')
|
||||
api_response = self._download_webpage(
|
||||
movie = self._download_json(
|
||||
self._MOVIE_TEMPLATE % movie_id, movie_id,
|
||||
'Downloading movie JSON')
|
||||
movie = json.loads(api_response)
|
||||
movie_name = movie['name']
|
||||
return self._extract_videos(movie_id, movie_name)
|
||||
|
||||
|
@@ -13,22 +13,24 @@ from ..utils import (
|
||||
compat_urllib_request,
|
||||
ExtractorError,
|
||||
url_basename,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class SmotriIE(InfoExtractor):
|
||||
IE_DESC = 'Smotri.com'
|
||||
IE_NAME = 'smotri'
|
||||
_VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
|
||||
_VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
|
||||
_NETRC_MACHINE = 'smotri'
|
||||
|
||||
_TESTS = [
|
||||
# real video id 2610366
|
||||
{
|
||||
'url': 'http://smotri.com/video/view/?id=v261036632ab',
|
||||
'file': 'v261036632ab.mp4',
|
||||
'md5': '2a7b08249e6f5636557579c368040eb9',
|
||||
'info_dict': {
|
||||
'id': 'v261036632ab',
|
||||
'ext': 'mp4',
|
||||
'title': 'катастрофа с камер видеонаблюдения',
|
||||
'uploader': 'rbc2008',
|
||||
'uploader_id': 'rbc08',
|
||||
@@ -40,9 +42,10 @@ class SmotriIE(InfoExtractor):
|
||||
# real video id 57591
|
||||
{
|
||||
'url': 'http://smotri.com/video/view/?id=v57591cb20',
|
||||
'file': 'v57591cb20.flv',
|
||||
'md5': '830266dfc21f077eac5afd1883091bcd',
|
||||
'info_dict': {
|
||||
'id': 'v57591cb20',
|
||||
'ext': 'flv',
|
||||
'title': 'test',
|
||||
'uploader': 'Support Photofile@photofile',
|
||||
'uploader_id': 'support-photofile',
|
||||
@@ -54,9 +57,10 @@ class SmotriIE(InfoExtractor):
|
||||
# video-password
|
||||
{
|
||||
'url': 'http://smotri.com/video/view/?id=v1390466a13c',
|
||||
'file': 'v1390466a13c.mp4',
|
||||
'md5': 'f6331cef33cad65a0815ee482a54440b',
|
||||
'info_dict': {
|
||||
'id': 'v1390466a13c',
|
||||
'ext': 'mp4',
|
||||
'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
|
||||
'uploader': 'timoxa40',
|
||||
'uploader_id': 'timoxa40',
|
||||
@@ -71,9 +75,10 @@ class SmotriIE(InfoExtractor):
|
||||
# age limit + video-password
|
||||
{
|
||||
'url': 'http://smotri.com/video/view/?id=v15408898bcf',
|
||||
'file': 'v15408898bcf.flv',
|
||||
'md5': '91e909c9f0521adf5ee86fbe073aad70',
|
||||
'info_dict': {
|
||||
'id': 'v15408898bcf',
|
||||
'ext': 'flv',
|
||||
'title': 'этот ролик не покажут по ТВ',
|
||||
'uploader': 'zzxxx',
|
||||
'uploader_id': 'ueggb',
|
||||
@@ -85,7 +90,22 @@ class SmotriIE(InfoExtractor):
|
||||
'params': {
|
||||
'videopassword': '333'
|
||||
}
|
||||
}
|
||||
},
|
||||
# swf player
|
||||
{
|
||||
'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
|
||||
'md5': '4d47034979d9390d14acdf59c4935bc2',
|
||||
'info_dict': {
|
||||
'id': 'v9188090500',
|
||||
'ext': 'mp4',
|
||||
'title': 'Shakira - Don\'t Bother',
|
||||
'uploader': 'HannahL',
|
||||
'uploader_id': 'lisaha95',
|
||||
'upload_date': '20090331',
|
||||
'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother',
|
||||
'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
_SUCCESS = 0
|
||||
@@ -93,6 +113,21 @@ class SmotriIE(InfoExtractor):
|
||||
_PASSWORD_DETECTED = 2
|
||||
_VIDEO_NOT_FOUND = 3
|
||||
|
||||
@classmethod
|
||||
def _extract_url(cls, webpage):
|
||||
mobj = re.search(
|
||||
r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
|
||||
webpage)
|
||||
if mobj is not None:
|
||||
return mobj.group('url')
|
||||
|
||||
mobj = re.search(
|
||||
r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
|
||||
<div\s+class="video_image">[^<]+</div>\s*
|
||||
<div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
|
||||
if mobj is not None:
|
||||
return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
|
||||
|
||||
def _search_meta(self, name, html, display_name=None):
|
||||
if display_name is None:
|
||||
display_name = name
|
||||
@@ -134,7 +169,7 @@ class SmotriIE(InfoExtractor):
|
||||
|
||||
# Video JSON does not provide enough meta data
|
||||
# We will extract some from the video web page instead
|
||||
video_page_url = 'http://' + mobj.group('url')
|
||||
video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id
|
||||
video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page')
|
||||
|
||||
# Warning if video is unavailable
|
||||
@@ -222,7 +257,7 @@ class SmotriIE(InfoExtractor):
|
||||
'upload_date': video_upload_date,
|
||||
'uploader_id': video_uploader_id,
|
||||
'duration': video_duration,
|
||||
'view_count': video_view_count,
|
||||
'view_count': int_or_none(video_view_count),
|
||||
'age_limit': 18 if adult_content else 0,
|
||||
'video_page_url': video_page_url
|
||||
}
|
||||
|
@@ -1,33 +1,37 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class TF1IE(InfoExtractor):
|
||||
"""TF1 uses the wat.tv player."""
|
||||
_VALID_URL = r'http://videos\.tf1\.fr/.*-(.*?)\.html'
|
||||
_VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html'
|
||||
_TEST = {
|
||||
u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
|
||||
u'file': u'10635995.mp4',
|
||||
u'md5': u'2e378cc28b9957607d5e88f274e637d8',
|
||||
u'info_dict': {
|
||||
u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
|
||||
u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
|
||||
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
|
||||
'info_dict': {
|
||||
'id': '10635995',
|
||||
'ext': 'mp4',
|
||||
'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
|
||||
'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
},
|
||||
u'skip': u'Sometimes wat serves the whole file with the --test option',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
id = mobj.group(1)
|
||||
webpage = self._download_webpage(url, id)
|
||||
embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
|
||||
webpage, 'embed url')
|
||||
embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
embed_url = self._html_search_regex(
|
||||
r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url')
|
||||
embed_page = self._download_webpage(embed_url, video_id,
|
||||
'Downloading embed player page')
|
||||
wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
|
||||
wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
|
||||
wat_info = json.loads(wat_info)['media']
|
||||
wat_url = wat_info['url']
|
||||
return self.url_result(wat_url, 'Wat')
|
||||
wat_info = self._download_json(
|
||||
'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
|
||||
return self.url_result(wat_info['media']['url'], 'Wat')
|
||||
|
@@ -6,6 +6,7 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urllib_parse,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@@ -24,6 +25,7 @@ class UrortIE(InfoExtractor):
|
||||
'like_count': int,
|
||||
'uploader': 'Gerilja',
|
||||
'uploader_id': 'Gerilja',
|
||||
'upload_date': '20100323',
|
||||
},
|
||||
'params': {
|
||||
'matchtitle': '^The Bomb$', # To test, we want just one video
|
||||
@@ -37,6 +39,7 @@ class UrortIE(InfoExtractor):
|
||||
fstr = compat_urllib_parse.quote("InternalBandUrl eq '%s'" % playlist_id)
|
||||
json_url = 'http://urort.p3.no/breeze/urort/TrackDtos?$filter=' + fstr
|
||||
songs = self._download_json(json_url, playlist_id)
|
||||
print(songs[0])
|
||||
|
||||
entries = [{
|
||||
'id': '%d-%s' % (s['BandId'], s['$id']),
|
||||
@@ -47,6 +50,7 @@ class UrortIE(InfoExtractor):
|
||||
'uploader': s.get('BandName', playlist_id),
|
||||
'like_count': s.get('LikeCount'),
|
||||
'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'],
|
||||
'upload_date': unified_strdate(s.get('Released')),
|
||||
} for s in songs]
|
||||
|
||||
return {
|
||||
|
@@ -16,7 +16,7 @@ from ..utils import (
|
||||
|
||||
class VKIE(InfoExtractor):
|
||||
IE_NAME = 'vk.com'
|
||||
_VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
|
||||
_VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
|
||||
_NETRC_MACHINE = 'vk'
|
||||
|
||||
_TESTS = [
|
||||
|
@@ -1,37 +1,37 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class WatIE(InfoExtractor):
|
||||
_VALID_URL=r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html'
|
||||
_VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html'
|
||||
IE_NAME = 'wat.tv'
|
||||
_TEST = {
|
||||
u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
|
||||
u'file': u'10631273.mp4',
|
||||
u'md5': u'd8b2231e1e333acd12aad94b80937e19',
|
||||
u'info_dict': {
|
||||
u'title': u'World War Z - Philadelphia VOST',
|
||||
u'description': u'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr',
|
||||
'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
|
||||
'info_dict': {
|
||||
'id': '10631273',
|
||||
'ext': 'mp4',
|
||||
'title': 'World War Z - Philadelphia VOST',
|
||||
'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr',
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
},
|
||||
u'skip': u'Sometimes wat serves the whole file with the --test option',
|
||||
}
|
||||
|
||||
|
||||
def download_video_info(self, real_id):
|
||||
# 'contentv4' is used in the website, but it also returns the related
|
||||
# videos, we don't need them
|
||||
info = self._download_webpage('http://www.wat.tv/interface/contentv3/' + real_id, real_id, 'Downloading video info')
|
||||
info = json.loads(info)
|
||||
info = self._download_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id)
|
||||
return info['media']
|
||||
|
||||
|
||||
def _real_extract(self, url):
|
||||
def real_id_for_chapter(chapter):
|
||||
return chapter['tc_start'].split('-')[0]
|
||||
@@ -56,17 +56,17 @@ class WatIE(InfoExtractor):
|
||||
entries = [self.url_result(chapter_url) for chapter_url in chapter_urls]
|
||||
return self.playlist_result(entries, real_id, video_info['title'])
|
||||
|
||||
upload_date = None
|
||||
if 'date_diffusion' in first_chapter:
|
||||
upload_date = unified_strdate(first_chapter['date_diffusion'])
|
||||
# Otherwise we can continue and extract just one part, we have to use
|
||||
# the short id for getting the video url
|
||||
info = {'id': real_id,
|
||||
'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
|
||||
'ext': 'mp4',
|
||||
'title': first_chapter['title'],
|
||||
'thumbnail': first_chapter['preview'],
|
||||
'description': first_chapter['description'],
|
||||
'view_count': video_info['views'],
|
||||
}
|
||||
if 'date_diffusion' in first_chapter:
|
||||
info['upload_date'] = unified_strdate(first_chapter['date_diffusion'])
|
||||
|
||||
return info
|
||||
return {
|
||||
'id': real_id,
|
||||
'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
|
||||
'title': first_chapter['title'],
|
||||
'thumbnail': first_chapter['preview'],
|
||||
'description': first_chapter['description'],
|
||||
'view_count': video_info['views'],
|
||||
'upload_date': upload_date,
|
||||
}
|
||||
|
@@ -4,9 +4,10 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
unified_strdate,
|
||||
compat_parse_qs,
|
||||
compat_urlparse,
|
||||
determine_ext,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@@ -111,4 +112,85 @@ class WDRIE(InfoExtractor):
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class WDRMausIE(InfoExtractor):
|
||||
_VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
|
||||
IE_DESC = 'Sendung mit der Maus'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
|
||||
'info_dict': {
|
||||
'id': 'aktuelle-sendung',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': 're:^http://.+\.jpg',
|
||||
'upload_date': 're:^[0-9]{8}$',
|
||||
'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
|
||||
'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
|
||||
'info_dict': {
|
||||
'id': '40_jahre_maus',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': 're:^http://.+\.jpg',
|
||||
'upload_date': '20131007',
|
||||
'title': '12.03.2011 - 40 Jahre Maus',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
param_code = self._html_search_regex(
|
||||
r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters')
|
||||
|
||||
title_date = self._search_regex(
|
||||
r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
|
||||
webpage, 'air date')
|
||||
title_str = self._html_search_regex(
|
||||
r'<h1>(.*?)</h1>', webpage, 'title')
|
||||
title = '%s - %s' % (title_date, title_str)
|
||||
upload_date = unified_strdate(
|
||||
self._html_search_meta('dc.date', webpage))
|
||||
|
||||
fields = compat_parse_qs(param_code)
|
||||
video_url = fields['firstVideo'][0]
|
||||
thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
|
||||
|
||||
formats = [{
|
||||
'format_id': 'rtmp',
|
||||
'url': video_url,
|
||||
}]
|
||||
|
||||
jscode = self._download_webpage(
|
||||
'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
|
||||
video_id, fatal=False,
|
||||
note='Downloading URL translation table',
|
||||
errnote='Could not download URL translation table')
|
||||
if jscode:
|
||||
for m in re.finditer(
|
||||
r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
|
||||
jscode):
|
||||
if video_url.startswith(m.group('stream')):
|
||||
http_url = video_url.replace(
|
||||
m.group('stream'), m.group('dl'))
|
||||
formats.append({
|
||||
'format_id': 'http',
|
||||
'url': http_url,
|
||||
})
|
||||
break
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
}
|
||||
|
||||
# TODO test _1
|
@@ -3,11 +3,12 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .youtube import YoutubeIE
|
||||
|
||||
|
||||
class WimpIE(InfoExtractor):
|
||||
_VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.wimp.com/maruexhausted/',
|
||||
'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
|
||||
'info_dict': {
|
||||
@@ -16,7 +17,20 @@ class WimpIE(InfoExtractor):
|
||||
'title': 'Maru is exhausted.',
|
||||
'description': 'md5:57e099e857c0a4ea312542b684a869b8',
|
||||
}
|
||||
}
|
||||
}, {
|
||||
# youtube video
|
||||
'url': 'http://www.wimp.com/clowncar/',
|
||||
'info_dict': {
|
||||
'id': 'cG4CEr2aiSg',
|
||||
'ext': 'mp4',
|
||||
'title': 'Basset hound clown car...incredible!',
|
||||
'description': 'md5:8d228485e0719898c017203f900b3a35',
|
||||
'uploader': 'Gretchen Hoey',
|
||||
'uploader_id': 'gretchenandjeff1',
|
||||
'upload_date': '20140303',
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@@ -24,6 +38,13 @@ class WimpIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_url = self._search_regex(
|
||||
r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL')
|
||||
if YoutubeIE.suitable(video_url):
|
||||
self.to_screen('Found YouTube video')
|
||||
return {
|
||||
'_type': 'url',
|
||||
'url': video_url,
|
||||
'ie_key': YoutubeIE.ie_key(),
|
||||
}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
@@ -31,4 +52,4 @@ class WimpIE(InfoExtractor):
|
||||
'title': self._og_search_title(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
'description': self._og_search_description(webpage),
|
||||
}
|
||||
}
|
||||
|
@@ -7,13 +7,13 @@ import itertools
|
||||
import json
|
||||
import os.path
|
||||
import re
|
||||
import string
|
||||
import struct
|
||||
import traceback
|
||||
import zlib
|
||||
|
||||
from .common import InfoExtractor, SearchInfoExtractor
|
||||
from .subtitles import SubtitlesInfoExtractor
|
||||
from ..jsinterp import JSInterpreter
|
||||
from ..utils import (
|
||||
compat_chr,
|
||||
compat_parse_qs,
|
||||
@@ -438,113 +438,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
|
||||
def _parse_sig_js(self, jscode):
|
||||
funcname = self._search_regex(
|
||||
r'signature=([a-zA-Z]+)', jscode,
|
||||
u'Initial JS player signature function name')
|
||||
u'Initial JS player signature function name')
|
||||
|
||||
functions = {}
|
||||
|
||||
def argidx(varname):
|
||||
return string.lowercase.index(varname)
|
||||
|
||||
def interpret_statement(stmt, local_vars, allow_recursion=20):
|
||||
if allow_recursion < 0:
|
||||
raise ExtractorError(u'Recursion limit reached')
|
||||
|
||||
if stmt.startswith(u'var '):
|
||||
stmt = stmt[len(u'var '):]
|
||||
ass_m = re.match(r'^(?P<out>[a-z]+)(?:\[(?P<index>[^\]]+)\])?' +
|
||||
r'=(?P<expr>.*)$', stmt)
|
||||
if ass_m:
|
||||
if ass_m.groupdict().get('index'):
|
||||
def assign(val):
|
||||
lvar = local_vars[ass_m.group('out')]
|
||||
idx = interpret_expression(ass_m.group('index'),
|
||||
local_vars, allow_recursion)
|
||||
assert isinstance(idx, int)
|
||||
lvar[idx] = val
|
||||
return val
|
||||
expr = ass_m.group('expr')
|
||||
else:
|
||||
def assign(val):
|
||||
local_vars[ass_m.group('out')] = val
|
||||
return val
|
||||
expr = ass_m.group('expr')
|
||||
elif stmt.startswith(u'return '):
|
||||
assign = lambda v: v
|
||||
expr = stmt[len(u'return '):]
|
||||
else:
|
||||
raise ExtractorError(
|
||||
u'Cannot determine left side of statement in %r' % stmt)
|
||||
|
||||
v = interpret_expression(expr, local_vars, allow_recursion)
|
||||
return assign(v)
|
||||
|
||||
def interpret_expression(expr, local_vars, allow_recursion):
|
||||
if expr.isdigit():
|
||||
return int(expr)
|
||||
|
||||
if expr.isalpha():
|
||||
return local_vars[expr]
|
||||
|
||||
m = re.match(r'^(?P<in>[a-z]+)\.(?P<member>.*)$', expr)
|
||||
if m:
|
||||
member = m.group('member')
|
||||
val = local_vars[m.group('in')]
|
||||
if member == 'split("")':
|
||||
return list(val)
|
||||
if member == 'join("")':
|
||||
return u''.join(val)
|
||||
if member == 'length':
|
||||
return len(val)
|
||||
if member == 'reverse()':
|
||||
return val[::-1]
|
||||
slice_m = re.match(r'slice\((?P<idx>.*)\)', member)
|
||||
if slice_m:
|
||||
idx = interpret_expression(
|
||||
slice_m.group('idx'), local_vars, allow_recursion-1)
|
||||
return val[idx:]
|
||||
|
||||
m = re.match(
|
||||
r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr)
|
||||
if m:
|
||||
val = local_vars[m.group('in')]
|
||||
idx = interpret_expression(m.group('idx'), local_vars,
|
||||
allow_recursion-1)
|
||||
return val[idx]
|
||||
|
||||
m = re.match(r'^(?P<a>.+?)(?P<op>[%])(?P<b>.+?)$', expr)
|
||||
if m:
|
||||
a = interpret_expression(m.group('a'),
|
||||
local_vars, allow_recursion)
|
||||
b = interpret_expression(m.group('b'),
|
||||
local_vars, allow_recursion)
|
||||
return a % b
|
||||
|
||||
m = re.match(
|
||||
r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr)
|
||||
if m:
|
||||
fname = m.group('func')
|
||||
if fname not in functions:
|
||||
functions[fname] = extract_function(fname)
|
||||
argvals = [int(v) if v.isdigit() else local_vars[v]
|
||||
for v in m.group('args').split(',')]
|
||||
return functions[fname](argvals)
|
||||
raise ExtractorError(u'Unsupported JS expression %r' % expr)
|
||||
|
||||
def extract_function(funcname):
|
||||
func_m = re.search(
|
||||
r'function ' + re.escape(funcname) +
|
||||
r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}',
|
||||
jscode)
|
||||
argnames = func_m.group('args').split(',')
|
||||
|
||||
def resf(args):
|
||||
local_vars = dict(zip(argnames, args))
|
||||
for stmt in func_m.group('code').split(';'):
|
||||
res = interpret_statement(stmt, local_vars)
|
||||
return res
|
||||
return resf
|
||||
|
||||
initial_function = extract_function(funcname)
|
||||
jsi = JSInterpreter(jscode)
|
||||
initial_function = jsi.extract_function(funcname)
|
||||
return lambda s: initial_function([s])
|
||||
|
||||
def _parse_sig_swf(self, file_contents):
|
||||
@@ -1549,7 +1446,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
|
||||
break
|
||||
|
||||
more = self._download_json(
|
||||
'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s' % page_num)
|
||||
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
|
||||
'Downloading page #%s' % page_num,
|
||||
transform_source=uppercase_escape)
|
||||
content_html = more['content_html']
|
||||
more_widget_html = more['load_more_widget_html']
|
||||
|
||||
@@ -1712,7 +1611,7 @@ class YoutubeUserIE(InfoExtractor):
|
||||
|
||||
class YoutubeSearchIE(SearchInfoExtractor):
|
||||
IE_DESC = u'YouTube.com searches'
|
||||
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
|
||||
_API_URL = u'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
|
||||
_MAX_RESULTS = 1000
|
||||
IE_NAME = u'youtube:search'
|
||||
_SEARCH_KEY = 'ytsearch'
|
||||
@@ -1723,9 +1622,12 @@ class YoutubeSearchIE(SearchInfoExtractor):
|
||||
video_ids = []
|
||||
pagenum = 0
|
||||
limit = n
|
||||
PAGE_SIZE = 50
|
||||
|
||||
while (50 * pagenum) < limit:
|
||||
result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
|
||||
while (PAGE_SIZE * pagenum) < limit:
|
||||
result_url = self._API_URL % (
|
||||
compat_urllib_parse.quote_plus(query.encode('utf-8')),
|
||||
(PAGE_SIZE * pagenum) + 1)
|
||||
data_json = self._download_webpage(
|
||||
result_url, video_id=u'query "%s"' % query,
|
||||
note=u'Downloading page %s' % (pagenum + 1),
|
||||
@@ -1836,11 +1738,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
|
||||
feed_entries = []
|
||||
paging = 0
|
||||
for i in itertools.count(1):
|
||||
info = self._download_webpage(self._FEED_TEMPLATE % paging,
|
||||
info = self._download_json(self._FEED_TEMPLATE % paging,
|
||||
u'%s feed' % self._FEED_NAME,
|
||||
u'Downloading page %s' % i)
|
||||
info = json.loads(info)
|
||||
feed_html = info['feed_html']
|
||||
feed_html = info.get('feed_html') or info.get('content_html')
|
||||
m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
|
||||
ids = orderedSet(m.group(1) for m in m_ids)
|
||||
feed_entries.extend(
|
||||
@@ -1852,7 +1753,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
|
||||
return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
|
||||
|
||||
class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
|
||||
IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword(requires authentication)'
|
||||
IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
|
||||
_VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
|
||||
_FEED_NAME = 'subscriptions'
|
||||
_PLAYLIST_TITLE = u'Youtube Subscriptions'
|
||||
|
116
youtube_dl/jsinterp.py
Normal file
116
youtube_dl/jsinterp.py
Normal file
@@ -0,0 +1,116 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .utils import (
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class JSInterpreter(object):
|
||||
def __init__(self, code):
|
||||
self.code = code
|
||||
self._functions = {}
|
||||
|
||||
def interpret_statement(self, stmt, local_vars, allow_recursion=20):
|
||||
if allow_recursion < 0:
|
||||
raise ExtractorError('Recursion limit reached')
|
||||
|
||||
if stmt.startswith('var '):
|
||||
stmt = stmt[len('var '):]
|
||||
ass_m = re.match(r'^(?P<out>[a-z]+)(?:\[(?P<index>[^\]]+)\])?' +
|
||||
r'=(?P<expr>.*)$', stmt)
|
||||
if ass_m:
|
||||
if ass_m.groupdict().get('index'):
|
||||
def assign(val):
|
||||
lvar = local_vars[ass_m.group('out')]
|
||||
idx = self.interpret_expression(
|
||||
ass_m.group('index'), local_vars, allow_recursion)
|
||||
assert isinstance(idx, int)
|
||||
lvar[idx] = val
|
||||
return val
|
||||
expr = ass_m.group('expr')
|
||||
else:
|
||||
def assign(val):
|
||||
local_vars[ass_m.group('out')] = val
|
||||
return val
|
||||
expr = ass_m.group('expr')
|
||||
elif stmt.startswith('return '):
|
||||
assign = lambda v: v
|
||||
expr = stmt[len('return '):]
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'Cannot determine left side of statement in %r' % stmt)
|
||||
|
||||
v = self.interpret_expression(expr, local_vars, allow_recursion)
|
||||
return assign(v)
|
||||
|
||||
def interpret_expression(self, expr, local_vars, allow_recursion):
|
||||
if expr.isdigit():
|
||||
return int(expr)
|
||||
|
||||
if expr.isalpha():
|
||||
return local_vars[expr]
|
||||
|
||||
m = re.match(r'^(?P<in>[a-z]+)\.(?P<member>.*)$', expr)
|
||||
if m:
|
||||
member = m.group('member')
|
||||
val = local_vars[m.group('in')]
|
||||
if member == 'split("")':
|
||||
return list(val)
|
||||
if member == 'join("")':
|
||||
return u''.join(val)
|
||||
if member == 'length':
|
||||
return len(val)
|
||||
if member == 'reverse()':
|
||||
return val[::-1]
|
||||
slice_m = re.match(r'slice\((?P<idx>.*)\)', member)
|
||||
if slice_m:
|
||||
idx = self.interpret_expression(
|
||||
slice_m.group('idx'), local_vars, allow_recursion - 1)
|
||||
return val[idx:]
|
||||
|
||||
m = re.match(
|
||||
r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr)
|
||||
if m:
|
||||
val = local_vars[m.group('in')]
|
||||
idx = self.interpret_expression(
|
||||
m.group('idx'), local_vars, allow_recursion - 1)
|
||||
return val[idx]
|
||||
|
||||
m = re.match(r'^(?P<a>.+?)(?P<op>[%])(?P<b>.+?)$', expr)
|
||||
if m:
|
||||
a = self.interpret_expression(
|
||||
m.group('a'), local_vars, allow_recursion)
|
||||
b = self.interpret_expression(
|
||||
m.group('b'), local_vars, allow_recursion)
|
||||
return a % b
|
||||
|
||||
m = re.match(
|
||||
r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr)
|
||||
if m:
|
||||
fname = m.group('func')
|
||||
if fname not in self._functions:
|
||||
self._functions[fname] = self.extract_function(fname)
|
||||
argvals = [int(v) if v.isdigit() else local_vars[v]
|
||||
for v in m.group('args').split(',')]
|
||||
return self._functions[fname](argvals)
|
||||
raise ExtractorError('Unsupported JS expression %r' % expr)
|
||||
|
||||
def extract_function(self, funcname):
|
||||
func_m = re.search(
|
||||
(r'(?:function %s|%s\s*=\s*function)' % (
|
||||
re.escape(funcname), re.escape(funcname))) +
|
||||
r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}',
|
||||
self.code)
|
||||
if func_m is None:
|
||||
raise ExtractorError('Could not find JS function %r' % funcname)
|
||||
argnames = func_m.group('args').split(',')
|
||||
|
||||
def resf(args):
|
||||
local_vars = dict(zip(argnames, args))
|
||||
for stmt in func_m.group('code').split(';'):
|
||||
res = self.interpret_statement(stmt, local_vars)
|
||||
return res
|
||||
return resf
|
||||
|
@@ -53,8 +53,9 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
|
||||
if self._downloader.params.get('verbose', False):
|
||||
self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd))
|
||||
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
stdout,stderr = p.communicate()
|
||||
bcmd = [self._downloader.encode(c) for c in cmd]
|
||||
p = subprocess.Popen(bcmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
stdout, stderr = p.communicate()
|
||||
if p.returncode != 0:
|
||||
stderr = stderr.decode('utf-8', 'replace')
|
||||
msg = stderr.strip().split('\n')[-1]
|
||||
|
@@ -539,7 +539,6 @@ def encodeFilename(s, for_subprocess=False):
|
||||
encoding = 'utf-8'
|
||||
return s.encode(encoding, 'ignore')
|
||||
|
||||
|
||||
def decodeOption(optval):
|
||||
if optval is None:
|
||||
return optval
|
||||
@@ -1177,8 +1176,12 @@ class HEADRequest(compat_urllib_request.Request):
|
||||
return "HEAD"
|
||||
|
||||
|
||||
def int_or_none(v, scale=1):
|
||||
return v if v is None else (int(v) // scale)
|
||||
def int_or_none(v, scale=1, default=None):
|
||||
return default if v is None else (int(v) // scale)
|
||||
|
||||
|
||||
def float_or_none(v, scale=1, default=None):
|
||||
return default if v is None else (float(v) / scale)
|
||||
|
||||
|
||||
def parse_duration(s):
|
||||
@@ -1261,8 +1264,8 @@ class PagedList(object):
|
||||
|
||||
def uppercase_escape(s):
|
||||
return re.sub(
|
||||
r'\\U([0-9a-fA-F]{8})',
|
||||
lambda m: compat_chr(int(m.group(1), base=16)), s)
|
||||
r'\\U[0-9a-fA-F]{8}',
|
||||
lambda m: m.group(0).decode('unicode-escape'), s)
|
||||
|
||||
try:
|
||||
struct.pack(u'!I', 0)
|
||||
|
@@ -1,2 +1,2 @@
|
||||
|
||||
__version__ = '2014.03.27.1'
|
||||
__version__ = '2014.04.04.3'
|
||||
|
Reference in New Issue
Block a user