1 from __future__ import unicode_literals
7 from .common import InfoExtractor, SearchInfoExtractor
16 class YahooIE(InfoExtractor):
17 IE_DESC = 'Yahoo screen'
18 _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
21 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
22 'file': '214727115.mp4',
23 'md5': '4962b075c08be8690a922ee026d05e69',
25 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
26 'description': 'Julian and Travis watch Julian Smith',
30 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
31 'file': '103000935.mp4',
32 'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
34 'title': 'Codefellas - The Cougar Lies with Spanish Moss',
35 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
40 def _real_extract(self, url):
41 mobj = re.match(self._VALID_URL, url)
42 video_id = mobj.group('id')
43 webpage = self._download_webpage(url, video_id)
45 items_json = self._search_regex(r'mediaItems: ({.*?})$',
46 webpage, 'items', flags=re.MULTILINE)
47 items = json.loads(items_json)
48 info = items['mediaItems']['query']['results']['mediaObj'][0]
49 # The 'meta' field is not always in the video webpage, we request it
52 return self._get_info(long_id, video_id)
54 def _get_info(self, long_id, video_id):
55 query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
56 ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"'
57 ' AND protocol="http"' % long_id)
58 data = compat_urllib_parse.urlencode({
63 query_result_json = self._download_webpage(
64 'http://video.query.yahoo.com/v1/public/yql?' + data,
65 video_id, 'Downloading video info')
66 query_result = json.loads(query_result_json)
67 info = query_result['query']['results']['mediaObj'][0]
71 for s in info['streams']:
73 'width': int_or_none(s.get('width')),
74 'height': int_or_none(s.get('height')),
75 'tbr': int_or_none(s.get('bitrate')),
80 if host.startswith('rtmp'):
87 format_url = compat_urlparse.urljoin(host, path)
88 format_info['url'] = format_url
90 formats.append(format_info)
92 self._sort_formats(formats)
96 'title': meta['title'],
98 'description': clean_html(meta['description']),
99 'thumbnail': meta['thumbnail'],
103 class YahooNewsIE(YahooIE):
104 IE_NAME = 'yahoo:news'
105 _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'
108 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
109 'md5': '67010fdf3a08d290e060a4dd96baa07b',
113 'title': 'China Moses Is Crazy About the Blues',
114 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
118 # Overwrite YahooIE properties we don't want
121 def _real_extract(self, url):
122 mobj = re.match(self._VALID_URL, url)
123 video_id = mobj.group('id')
124 webpage = self._download_webpage(url, video_id)
125 long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id')
126 return self._get_info(long_id, video_id)
129 class YahooSearchIE(SearchInfoExtractor):
130 IE_DESC = 'Yahoo screen search'
132 IE_NAME = 'screen.yahoo:search'
133 _SEARCH_KEY = 'yvsearch'
135 def _get_n_results(self, query, n):
136 """Get a specified number of results for a query"""
143 for pagenum in itertools.count(0):
144 result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
145 webpage = self._download_webpage(result_url, query,
146 note='Downloading results page '+str(pagenum+1))
147 info = json.loads(webpage)
149 results = info['results']
151 for (i, r) in enumerate(results):
152 if (pagenum * 30) +i >= n:
154 mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
155 e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
156 res['entries'].append(e)
157 if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)):