]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/metacafe.py
Prepare for release.
[youtubedl] / youtube_dl / extractor / metacafe.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 compat_parse_qs,
8 compat_urllib_parse,
9 compat_urllib_request,
10 determine_ext,
11 ExtractorError,
12 )
13
14
15 class MetacafeIE(InfoExtractor):
16 _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
17 _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
18 _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
19 IE_NAME = 'metacafe'
20 _TESTS = [
21 # Youtube video
22 {
23 'add_ie': ['Youtube'],
24 'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
25 'info_dict': {
26 'id': '_aUehQsCQtM',
27 'ext': 'mp4',
28 'upload_date': '20090102',
29 'title': 'The Electric Company | "Short I" | PBS KIDS GO!',
30 'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
31 'uploader': 'PBS',
32 'uploader_id': 'PBS'
33 }
34 },
35 # Normal metacafe video
36 {
37 'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
38 'md5': '6e0bca200eaad2552e6915ed6fd4d9ad',
39 'info_dict': {
40 'id': '11121940',
41 'ext': 'mp4',
42 'title': 'News: Stuff You Won\'t Do with Your PlayStation 4',
43 'uploader': 'ign',
44 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
45 },
46 },
47 # AnyClip video
48 {
49 'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
50 'info_dict': {
51 'id': 'an-dVVXnuY7Jh77J',
52 'ext': 'mp4',
53 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
54 'uploader': 'anyclip',
55 'description': 'md5:38c711dd98f5bb87acf973d573442e67',
56 },
57 },
58 # age-restricted video
59 {
60 'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
61 'md5': '98dde7c1a35d02178e8ab7560fe8bd09',
62 'info_dict': {
63 'id': '5186653',
64 'ext': 'mp4',
65 'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
66 'uploader': 'Dwayne Pipe',
67 'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b',
68 'age_limit': 18,
69 },
70 },
71 # cbs video
72 {
73 'url': 'http://www.metacafe.com/watch/cb-8VD4r_Zws8VP/open_this_is_face_the_nation_february_9/',
74 'info_dict': {
75 'id': '8VD4r_Zws8VP',
76 'ext': 'flv',
77 'title': 'Open: This is Face the Nation, February 9',
78 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
79 'duration': 96,
80 },
81 'params': {
82 # rtmp download
83 'skip_download': True,
84 },
85 },
86 ]
87
88 def report_disclaimer(self):
89 self.to_screen('Retrieving disclaimer')
90
91 def _real_initialize(self):
92 # Retrieve disclaimer
93 self.report_disclaimer()
94 self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
95
96 # Confirm age
97 disclaimer_form = {
98 'filters': '0',
99 'submit': "Continue - I'm over 18",
100 }
101 request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
102 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
103 self.report_age_confirmation()
104 self._download_webpage(request, None, False, 'Unable to confirm age')
105
106 def _real_extract(self, url):
107 # Extract id and simplified title from URL
108 mobj = re.match(self._VALID_URL, url)
109 if mobj is None:
110 raise ExtractorError('Invalid URL: %s' % url)
111
112 video_id = mobj.group(1)
113
114 # the video may come from an external site
115 m_external = re.match('^(\w{2})-(.*)$', video_id)
116 if m_external is not None:
117 prefix, ext_id = m_external.groups()
118 # Check if video comes from YouTube
119 if prefix == 'yt':
120 return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube')
121 # CBS videos use theplatform.com
122 if prefix == 'cb':
123 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
124
125 # Retrieve video webpage to extract further information
126 req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
127
128 # AnyClip videos require the flashversion cookie so that we get the link
129 # to the mp4 file
130 mobj_an = re.match(r'^an-(.*?)$', video_id)
131 if mobj_an:
132 req.headers['Cookie'] = 'flashVersion=0;'
133 webpage = self._download_webpage(req, video_id)
134
135 # Extract URL, uploader and title from webpage
136 self.report_extraction(video_id)
137 mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
138 if mobj is not None:
139 mediaURL = compat_urllib_parse.unquote(mobj.group(1))
140 video_ext = mediaURL[-3:]
141
142 # Extract gdaKey if available
143 mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
144 if mobj is None:
145 video_url = mediaURL
146 else:
147 gdaKey = mobj.group(1)
148 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
149 else:
150 mobj = re.search(r'<video src="([^"]+)"', webpage)
151 if mobj:
152 video_url = mobj.group(1)
153 video_ext = 'mp4'
154 else:
155 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
156 if mobj is None:
157 raise ExtractorError('Unable to extract media URL')
158 vardict = compat_parse_qs(mobj.group(1))
159 if 'mediaData' not in vardict:
160 raise ExtractorError('Unable to extract media URL')
161 mobj = re.search(
162 r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
163 if mobj is None:
164 raise ExtractorError('Unable to extract media URL')
165 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
166 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
167 video_ext = determine_ext(video_url)
168
169 video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title')
170 description = self._og_search_description(webpage)
171 thumbnail = self._og_search_thumbnail(webpage)
172 video_uploader = self._html_search_regex(
173 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
174 webpage, 'uploader nickname', fatal=False)
175
176 if re.search(r'"contentRating":"restricted"', webpage) is not None:
177 age_limit = 18
178 else:
179 age_limit = 0
180
181 return {
182 'id': video_id,
183 'url': video_url,
184 'description': description,
185 'uploader': video_uploader,
186 'title': video_title,
187 'thumbnail':thumbnail,
188 'ext': video_ext,
189 'age_limit': age_limit,
190 }