[livestream] Modernize

This commit is contained in:
Sergey M․ 2014-06-12 20:42:46 +07:00
parent 4d2f143ce5
commit c5469e046a

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import json import json
@ -6,31 +8,34 @@ from ..utils import (
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
compat_urlparse, compat_urlparse,
xpath_with_ns, xpath_with_ns,
compat_str,
) )
class LivestreamIE(InfoExtractor): class LivestreamIE(InfoExtractor):
IE_NAME = u'livestream' IE_NAME = 'livestream'
_VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_TEST = { _TEST = {
u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', 'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
u'file': u'4719370.mp4', 'md5': '53274c76ba7754fb0e8d072716f2292b',
u'md5': u'0d2186e3187d185a04b3cdd02b828836', 'info_dict': {
u'info_dict': { 'id': '4719370',
u'title': u'Live from Webster Hall NYC', 'ext': 'mp4',
u'upload_date': u'20121012', 'title': 'Live from Webster Hall NYC',
'upload_date': '20121012',
} }
} }
def _extract_video_info(self, video_data): def _extract_video_info(self, video_data):
video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url') video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
return {'id': video_data['id'], return {
'url': video_url, 'id': compat_str(video_data['id']),
'ext': 'mp4', 'url': video_url,
'title': video_data['caption'], 'ext': 'mp4',
'thumbnail': video_data['thumbnail_url'], 'title': video_data['caption'],
'upload_date': video_data['updated_at'].replace('-','')[:8], 'thumbnail': video_data['thumbnail_url'],
} 'upload_date': video_data['updated_at'].replace('-', '')[:8],
}
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -40,36 +45,36 @@ class LivestreamIE(InfoExtractor):
if video_id is None: if video_id is None:
# This is an event page: # This is an event page:
config_json = self._search_regex(r'window.config = ({.*?});', config_json = self._search_regex(
webpage, u'window config') r'window.config = ({.*?});', webpage, 'window config')
info = json.loads(config_json)['event'] info = json.loads(config_json)['event']
videos = [self._extract_video_info(video_data['data']) videos = [self._extract_video_info(video_data['data'])
for video_data in info['feed']['data'] if video_data['type'] == u'video'] for video_data in info['feed']['data'] if video_data['type'] == 'video']
return self.playlist_result(videos, info['id'], info['full_name']) return self.playlist_result(videos, info['id'], info['full_name'])
else: else:
og_video = self._og_search_video_url(webpage, name=u'player url') og_video = self._og_search_video_url(webpage, 'player url')
query_str = compat_urllib_parse_urlparse(og_video).query query_str = compat_urllib_parse_urlparse(og_video).query
query = compat_urlparse.parse_qs(query_str) query = compat_urlparse.parse_qs(query_str)
api_url = query['play_url'][0].replace('.smil', '') api_url = query['play_url'][0].replace('.smil', '')
info = json.loads(self._download_webpage(api_url, video_id, info = json.loads(self._download_webpage(
u'Downloading video info')) api_url, video_id, 'Downloading video info'))
return self._extract_video_info(info) return self._extract_video_info(info)
# The original version of Livestream uses a different system # The original version of Livestream uses a different system
class LivestreamOriginalIE(InfoExtractor): class LivestreamOriginalIE(InfoExtractor):
IE_NAME = u'livestream:original' IE_NAME = 'livestream:original'
_VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)' _VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)'
_TEST = { _TEST = {
u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', 'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
u'info_dict': { 'info_dict': {
u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb', 'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
u'ext': u'flv', 'ext': 'flv',
u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital', 'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
}, },
u'params': { 'params': {
# rtmp # rtmp
u'skip_download': True, 'skip_download': True,
}, },
} }
@ -84,7 +89,7 @@ class LivestreamOriginalIE(InfoExtractor):
ns = {'media': 'http://search.yahoo.com/mrss'} ns = {'media': 'http://search.yahoo.com/mrss'}
thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url'] thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
# Remove the extension and number from the path (like 1.jpg) # Remove the extension and number from the path (like 1.jpg)
path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path') path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')
return { return {
'id': video_id, 'id': video_id,