Fix "invalid escape sequences" error on Python 3.6
[youtube-dl] / youtube_dl / extractor / foxnews.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .amp import AMPIE
6 from .common import InfoExtractor
7
8
9 class FoxNewsIE(AMPIE):
10     IE_NAME = 'foxnews'
11     IE_DESC = 'Fox News and Fox Business Video'
12     _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
13     _TESTS = [
14         {
15             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
16             'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
17             'info_dict': {
18                 'id': '3937480',
19                 'ext': 'flv',
20                 'title': 'Frozen in Time',
21                 'description': '16-year-old girl is size of toddler',
22                 'duration': 265,
23                 'timestamp': 1304411491,
24                 'upload_date': '20110503',
25                 'thumbnail': r're:^https?://.*\.jpg$',
26             },
27         },
28         {
29             'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
30             'md5': '5846c64a1ea05ec78175421b8323e2df',
31             'info_dict': {
32                 'id': '3922535568001',
33                 'ext': 'mp4',
34                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
35                 'description': "Congressman discusses president's plan",
36                 'duration': 292,
37                 'timestamp': 1417662047,
38                 'upload_date': '20141204',
39                 'thumbnail': r're:^https?://.*\.jpg$',
40             },
41             'params': {
42                 # m3u8 download
43                 'skip_download': True,
44             },
45         },
46         {
47             'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
48             'only_matching': True,
49         },
50         {
51             'url': 'http://video.foxbusiness.com/v/4442309889001',
52             'only_matching': True,
53         },
54         {
55             # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
56             'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
57             'only_matching': True,
58         },
59     ]
60
61     def _real_extract(self, url):
62         host, video_id = re.match(self._VALID_URL, url).groups()
63
64         info = self._extract_feed_info(
65             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
66         info['id'] = video_id
67         return info
68
69
70 class FoxNewsArticleIE(InfoExtractor):
71     _VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
72     IE_NAME = 'foxnews:article'
73
74     _TEST = {
75         'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
76         'md5': '62aa5a781b308fdee212ebb6f33ae7ef',
77         'info_dict': {
78             'id': '5116295019001',
79             'ext': 'mp4',
80             'title': 'Trump and Clinton asked to defend positions on Iraq War',
81             'description': 'Veterans react on \'The Kelly File\'',
82             'timestamp': 1473299755,
83             'upload_date': '20160908',
84         },
85     }
86
87     def _real_extract(self, url):
88         display_id = self._match_id(url)
89         webpage = self._download_webpage(url, display_id)
90
91         video_id = self._html_search_regex(
92             r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
93             webpage, 'video ID', group='id')
94         return self.url_result(
95             'http://video.foxnews.com/v/' + video_id,
96             FoxNewsIE.ie_key())
97
98
99 class FoxNewsInsiderIE(InfoExtractor):
100     _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
101     IE_NAME = 'foxnews:insider'
102
103     _TEST = {
104         'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
105         'md5': 'a10c755e582d28120c62749b4feb4c0c',
106         'info_dict': {
107             'id': '5099377331001',
108             'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
109             'ext': 'mp4',
110             'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
111             'description': 'Is campus censorship getting out of control?',
112             'timestamp': 1472168725,
113             'upload_date': '20160825',
114             'thumbnail': r're:^https?://.*\.jpg$',
115         },
116         'params': {
117             # m3u8 download
118             'skip_download': True,
119         },
120         'add_ie': [FoxNewsIE.ie_key()],
121     }
122
123     def _real_extract(self, url):
124         display_id = self._match_id(url)
125
126         webpage = self._download_webpage(url, display_id)
127
128         embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
129
130         title = self._og_search_title(webpage)
131         description = self._og_search_description(webpage)
132
133         return {
134             '_type': 'url_transparent',
135             'ie_key': FoxNewsIE.ie_key(),
136             'url': embed_url,
137             'display_id': display_id,
138             'title': title,
139             'description': description,
140         }