depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-26 20:22:14 +00:00
Code Issues Releases Wiki Activity

YahooIE: support more videos

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-05-12 17:05:43 +02:00
parent 59f4fd4dc6
commit 2f58b12dad
1 changed files with 46 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

71
youtube_dl/InfoExtractors.py
View file

@ -920,36 +920,57 @@ class YahooIE(InfoExtractor):
if mobj is None: if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
m_id = re.search(r'YUI\.namespace\("Media"\)\.CONTENT_ID = "(?P<new_id>.+?)";', webpage)
# TODO: Check which url parameters are required if m_id is None:
info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id # TODO: Check which url parameters are required
webpage = self._download_webpage(info_url, video_id, "Downloading info webpage") info_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;lmsoverride=1;outputformat=mrss;cb=974419660;id=%s;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.* webpage = self._download_webpage(info_url, video_id, u'Downloading info webpage')
<description><!\[CDATA\[(?P<description>.*?)\]\]></description>.* info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]></title>.*
<media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.* <description><!\[CDATA\[(?P<description>.*?)\]\]></description>.*
<media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB" <media:pubStart><!\[CDATA\[(?P<date>.*?)\ .*\]\]></media:pubStart>.*
''' <media:content\ medium="image"\ url="(?P<thumb>.*?)"\ name="LARGETHUMB"
self.report_extraction(video_id) '''
m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL) self.report_extraction(video_id)
if m_info is None: m_info = re.search(info_re, webpage, re.VERBOSE|re.DOTALL)
raise ExtractorError(u'Unable to extract video info') if m_info is None:
video_title = m_info.group('title') raise ExtractorError(u'Unable to extract video info')
video_description = m_info.group('description') video_title = m_info.group('title')
video_thumb = m_info.group('thumb') video_description = m_info.group('description')
video_date = m_info.group('date') video_thumb = m_info.group('thumb')
video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d') video_date = m_info.group('date')
video_date = datetime.datetime.strptime(video_date, '%m/%d/%Y').strftime('%Y%m%d')
# TODO: Find a way to get mp4 videos # TODO: Find a way to get mp4 videos
rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id rest_url = 'http://cosmos.bcst.yahoo.com/rest/v2/pops;element=stream;outputformat=mrss;id=%s;lmsoverride=1;bw=375;dynamicstream=1;cb=83521105;tech=flv,mp4;rd=news.yahoo.com;datacontext=mdb;lg=KCa2IihxG3qE60vQ7HtyUy' % video_id
webpage = self._download_webpage(rest_url, video_id, 'Downloading video url webpage') webpage = self._download_webpage(rest_url, video_id, u'Downloading video url webpage')
m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage) m_rest = re.search(r'<media:content url="(?P<url>.*?)" path="(?P<path>.*?)"', webpage)
if m_rest is None: video_url = m_rest.group('url')
raise ExtractorError(u'Unable to extract video url') video_path = m_rest.group('path')
if m_rest is None:
raise ExtractorError(u'Unable to extract video url')
else: # We have to use a different method if another id is defined
long_id = m_id.group('new_id')
info_url = 'http://video.query.yahoo.com/v1/public/yql?q=SELECT%20*%20FROM%20yahoo.media.video.streams%20WHERE%20id%3D%22' + long_id + '%22%20AND%20format%3D%22mp4%2Cflv%22%20AND%20protocol%3D%22rtmp%2Chttp%22%20AND%20plrs%3D%2286Gj0vCaSzV_Iuf6hNylf2%22%20AND%20acctid%3D%22389%22%20AND%20plidl%3D%22%22%20AND%20pspid%3D%22792700001%22%20AND%20offnetwork%3D%22false%22%20AND%20site%3D%22ivy%22%20AND%20lang%3D%22en-US%22%20AND%20region%3D%22US%22%20AND%20override%3D%22none%22%3B&env=prod&format=json&callback=YUI.Env.JSONP.yui_3_8_1_1_1368368376830_335'
webpage = self._download_webpage(info_url, video_id, u'Downloading info json')
json_str = re.search(r'YUI.Env.JSONP.yui.*?\((.*?)\);', webpage).group(1)
info = json.loads(json_str)
res = info[u'query'][u'results'][u'mediaObj'][0]
stream = res[u'streams'][0]
video_path = stream[u'path']
video_url = stream[u'host']
meta = res[u'meta']
video_title = meta[u'title']
video_description = meta[u'description']
video_thumb = meta[u'thumbnail']
video_date = None # I can't find it
info_dict = { info_dict = {
'id': video_id, 'id': video_id,
'url':m_rest.group('url'), 'url': video_url,
'play_path': m_rest.group('path'), 'play_path': video_path,
'title':video_title, 'title':video_title,
'description': video_description, 'description': video_description,
'thumbnail': video_thumb, 'thumbnail': video_thumb,