1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
# coding: utf-8
from __future__ import unicode_literals
import itertools
import json
import re
from .common import InfoExtractor, SearchInfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urlparse,
clean_html,
int_or_none,
)
class YahooIE(InfoExtractor):
IE_DESC = 'Yahoo screen and movies'
_VALID_URL = r'(?P<url>https?://(?:.+?\.)?(?:screen|movies)\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)'
_TESTS = [
{
'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
'md5': '4962b075c08be8690a922ee026d05e69',
'info_dict': {
'id': '2d25e626-2378-391f-ada0-ddaf1417e588',
'ext': 'mp4',
'title': 'Julian Smith & Travis Legg Watch Julian Smith',
'description': 'Julian and Travis watch Julian Smith',
'duration': 6863,
},
},
{
'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
'info_dict': {
'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9',
'ext': 'mp4',
'title': 'Codefellas - The Cougar Lies with Spanish Moss',
'description': 'md5:66b627ab0a282b26352136ca96ce73c1',
'duration': 151,
},
},
{
'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed',
'md5': '60e8ac193d8fb71997caa8fce54c6460',
'info_dict': {
'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb',
'ext': 'mp4',
'title': "Yahoo Saves 'Community'",
'description': 'md5:4d4145af2fd3de00cbb6c1d664105053',
'duration': 170,
}
},
{
'url': 'https://tw.screen.yahoo.com/taipei-opinion-poll/選情站報-街頭民調-台北市篇-102823042.html',
'md5': '92a7fdd8a08783c68a174d7aa067dde8',
'info_dict': {
'id': '7a23b569-7bea-36cb-85b9-bd5301a0a1fb',
'ext': 'mp4',
'title': '選情站報 街頭民調 台北市篇',
'description': '選情站報 街頭民調 台北市篇',
'duration': 429,
}
},
{
'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html ',
'md5': '0b51660361f0e27c9789e7037ef76f4b',
'info_dict': {
'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58',
'ext': 'mp4',
'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder',
'description': 'md5:f66c890e1490f4910a9953c941dee944',
'duration': 97,
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = mobj.group('url')
webpage = self._download_webpage(url, video_id)
items_json = self._search_regex(
r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
default=None)
if items_json is None:
CONTENT_ID_REGEXES = [
r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
r'"first_videoid"\s*:\s*"([^"]+)"',
]
long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
video_id = long_id
else:
items = json.loads(items_json)
info = items['mediaItems']['query']['results']['mediaObj'][0]
# The 'meta' field is not always in the video webpage, we request it
# from another page
long_id = info['id']
return self._get_info(long_id, video_id, webpage)
def _get_info(self, long_id, video_id, webpage):
region = self._search_regex(
r'"region"\s*:\s*"([^"]+)"', webpage, 'region', fatal=False, default='US')
query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="%s"'
' AND protocol="http"' % (long_id, region))
data = compat_urllib_parse.urlencode({
'q': query,
'env': 'prod',
'format': 'json',
})
query_result = self._download_json(
'http://video.query.yahoo.com/v1/public/yql?' + data,
video_id, 'Downloading video info')
info = query_result['query']['results']['mediaObj'][0]
meta = info['meta']
formats = []
for s in info['streams']:
format_info = {
'width': int_or_none(s.get('width')),
'height': int_or_none(s.get('height')),
'tbr': int_or_none(s.get('bitrate')),
}
host = s['host']
path = s['path']
if host.startswith('rtmp'):
format_info.update({
'url': host,
'play_path': path,
'ext': 'flv',
})
else:
format_url = compat_urlparse.urljoin(host, path)
format_info['url'] = format_url
formats.append(format_info)
self._sort_formats(formats)
return {
'id': video_id,
'title': meta['title'],
'formats': formats,
'description': clean_html(meta['description']),
'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage),
'duration': int_or_none(meta.get('duration')),
}
class YahooNewsIE(YahooIE):
IE_NAME = 'yahoo:news'
_VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'
_TESTS = [{
'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
'md5': '67010fdf3a08d290e060a4dd96baa07b',
'info_dict': {
'id': '104538833',
'ext': 'mp4',
'title': 'China Moses Is Crazy About the Blues',
'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id')
return self._get_info(long_id, video_id, webpage)
class YahooSearchIE(SearchInfoExtractor):
IE_DESC = 'Yahoo screen search'
_MAX_RESULTS = 1000
IE_NAME = 'screen.yahoo:search'
_SEARCH_KEY = 'yvsearch'
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
entries = []
for pagenum in itertools.count(0):
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)
info = self._download_json(result_url, query,
note='Downloading results page '+str(pagenum+1))
m = info['m']
results = info['results']
for (i, r) in enumerate(results):
if (pagenum * 30) + i >= n:
break
mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
entries.append(e)
if (pagenum * 30 + i >= n) or (m['last'] >= (m['total'] - 1)):
break
return {
'_type': 'playlist',
'id': query,
'entries': entries,
}
|
