1 from __future__ import unicode_literals
7 from .common import InfoExtractor, SearchInfoExtractor
16 class YahooIE(InfoExtractor):
17 IE_DESC = 'Yahoo screen and movies'
18 _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html'
21 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
22 'md5': '4962b075c08be8690a922ee026d05e69',
26 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
27 'description': 'Julian and Travis watch Julian Smith',
31 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
32 'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
36 'title': 'Codefellas - The Cougar Lies with Spanish Moss',
37 '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?',
41 'url': 'https://movies.yahoo.com/video/world-loves-spider-man-190819223.html',
42 'md5': '410b7104aa9893b765bc22787a22f3d9',
44 'id': '516ed8e2-2c4f-339f-a211-7a8b49d30845',
46 'title': 'The World Loves Spider-Man',
47 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''',
52 def _real_extract(self, url):
53 mobj = re.match(self._VALID_URL, url)
54 video_id = mobj.group('id')
55 webpage = self._download_webpage(url, video_id)
57 items_json = self._search_regex(
58 r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
60 if items_json is None:
61 long_id = self._search_regex(
62 r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
63 webpage, 'content ID')
66 items = json.loads(items_json)
67 info = items['mediaItems']['query']['results']['mediaObj'][0]
68 # The 'meta' field is not always in the video webpage, we request it
71 return self._get_info(long_id, video_id)
73 def _get_info(self, long_id, video_id):
74 query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
75 ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"'
76 ' AND protocol="http"' % long_id)
77 data = compat_urllib_parse.urlencode({
82 query_result = self._download_json(
83 'http://video.query.yahoo.com/v1/public/yql?' + data,
84 video_id, 'Downloading video info')
85 info = query_result['query']['results']['mediaObj'][0]
89 for s in info['streams']:
91 'width': int_or_none(s.get('width')),
92 'height': int_or_none(s.get('height')),
93 'tbr': int_or_none(s.get('bitrate')),
98 if host.startswith('rtmp'):
105 format_url = compat_urlparse.urljoin(host, path)
106 format_info['url'] = format_url
107 formats.append(format_info)
109 self._sort_formats(formats)
113 'title': meta['title'],
115 'description': clean_html(meta['description']),
116 'thumbnail': meta['thumbnail'],
120 class YahooNewsIE(YahooIE):
121 IE_NAME = 'yahoo:news'
122 _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'
125 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
126 'md5': '67010fdf3a08d290e060a4dd96baa07b',
130 'title': 'China Moses Is Crazy About the Blues',
131 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
135 def _real_extract(self, url):
136 mobj = re.match(self._VALID_URL, url)
137 video_id = mobj.group('id')
138 webpage = self._download_webpage(url, video_id)
139 long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id')
140 return self._get_info(long_id, video_id)
143 class YahooSearchIE(SearchInfoExtractor):
144 IE_DESC = 'Yahoo screen search'
146 IE_NAME = 'screen.yahoo:search'
147 _SEARCH_KEY = 'yvsearch'
149 def _get_n_results(self, query, n):
150 """Get a specified number of results for a query"""
152 for pagenum in itertools.count(0):
153 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)
154 info = self._download_json(result_url, query,
155 note='Downloading results page '+str(pagenum+1))
157 results = info['results']
159 for (i, r) in enumerate(results):
160 if (pagenum * 30) + i >= n:
162 mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
163 e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
165 if (pagenum * 30 + i >= n) or (m['last'] >= (m['total'] - 1)):