mirrors/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[canvas] Improve (Closes #7145)

Browse Source
This commit is contained in:
Sergey M․ 2016-01-14 23:15:12 +06:00
parent be2d40a58a
commit 4e2743abd9
1 changed files with 38 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

91
youtube_dl/extractor/canvas.py
View File

@ -1,80 +1,65 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import os
import urlparse
from youtube_dl import utils
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import float_or_none
class CanvasIE(InfoExtractor): class CanvasIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?canvas\.be/video/(?P<id>.+)' _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = { _TEST = {
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week', 'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
'md5': 'ea838375a547ac787d4064d8c7860a6c', 'md5': 'ea838375a547ac787d4064d8c7860a6c',
'info_dict': { 'info_dict': {
'id': 'de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week', 'id': 'mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
'title': 'De afspraak veilt voor de Warmste Week', 'display_id': 'de-afspraak-veilt-voor-de-warmste-week',
'ext': 'mp4', 'ext': 'mp4',
'duration': 49, 'title': 'De afspraak veilt voor de Warmste Week',
'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 49.02,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
title = self._search_regex( title = self._search_regex(
r'<h1 class="video__body__header__title">(.+?)</h1>', webpage, r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
'title') webpage, 'title', default=None) or self._og_search_title(webpage)
data_video = self._html_search_regex(
r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'data-video', group='id') video_id = self._html_search_regex(
json_url = 'https://mediazone.vrt.be/api/v1/canvas/assets/' + data_video r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
data = self._download_json(json_url, video_id)
data = self._download_json(
'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
formats = [] formats = []
for target in data['targetUrls']: for target in data['targetUrls']:
if 'type' and 'url' in target: format_url, format_type = target.get('url'), target.get('type')
extension = utils.determine_ext(target['url']) if not format_url or not format_type:
if target['type'] == 'PROGRESSIVE_DOWNLOAD': continue
formats.append({ if format_type == 'HLS':
'format_id': extension, formats.extend(self._extract_m3u8_formats(
'url': target['url'], format_url, display_id, entry_protocol='m3u8_native',
'protocol': 'http', ext='mp4', preference=0, fatal=False, m3u8_id=format_type))
}) elif format_type == 'HDS':
elif target['type'] == 'HLS': formats.extend(self._extract_f4m_formats(
formats.extend(self._extract_m3u8_formats( format_url, display_id, f4m_id=format_type, fatal=False))
target['url'], video_id, entry_protocol='m3u8_native', else:
ext='mp4', formats.append({
preference=0, 'format_id': format_type,
fatal=False, 'url': format_url,
m3u8_id='hls')) })
elif target['type'] == 'HDS':
formats.append({
'format_id': extension,
'url': target['url'],
'protocol': 'HDS',
})
elif target['type'] == 'RTMP':
formats.append({
'format_id': extension,
'url': target['url'],
'protocol': 'rtmp',
})
elif target['type'] == 'RTSP':
formats.append({
'format_id': extension,
'url': target['url'],
'protocol': 'rtsp',
})
self._sort_formats(formats) self._sort_formats(formats)
duration = utils.int_or_none(data.get('duration')) / 1000
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage),
'formats': formats, 'formats': formats,
'duration': duration, 'duration': float_or_none(data.get('duration'), 1000),
'thumbnail': data.get('posterImageUrl'),
} }