]>
Commit | Line | Data |
---|---|---|
9eb4f404 S |
1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
f58487b3 TV |
3 | |
4 | import re | |
cc1ac110 | 5 | import itertools |
f58487b3 | 6 | |
9eb4f404 | 7 | from .common import InfoExtractor |
7073015a | 8 | from ..utils import urlencode_postdata |
9eb4f404 S |
9 | |
10 | ||
11 | class VierIE(InfoExtractor): | |
12 | IE_NAME = 'vier' | |
e129fa08 | 13 | IE_DESC = 'vier.be and vijf.be' |
a3ba8a7a | 14 | _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))' |
89fd0307 | 15 | _NETRC_MACHINE = 'vier' |
9eb4f404 S |
16 | _TESTS = [{ |
17 | 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', | |
7073015a | 18 | 'md5': 'e4ae2054a6b040ef1e289e20d111b46e', |
9eb4f404 S |
19 | 'info_dict': { |
20 | 'id': '16129', | |
21 | 'display_id': 'het-wordt-warm-de-moestuin', | |
22 | 'ext': 'mp4', | |
23 | 'title': 'Het wordt warm in De Moestuin', | |
24 | 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', | |
25 | }, | |
a3ba8a7a LV |
26 | }, { |
27 | 'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614', | |
28 | 'info_dict': { | |
29 | 'id': '2561614', | |
30 | 'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas', | |
31 | 'ext': 'mp4', | |
7073015a S |
32 | 'title': 'md5:84f45fe48b8c1fa296a7f6d208d080a7', |
33 | 'description': 'md5:0356d4981e58b8cbee19355cbd51a8fe', | |
a3ba8a7a LV |
34 | }, |
35 | 'params': { | |
a3ba8a7a LV |
36 | 'skip_download': True, |
37 | }, | |
89fd0307 | 38 | }, { |
39 | 'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839', | |
40 | 'info_dict': { | |
41 | 'id': '2674839', | |
42 | 'display_id': 'jani-gaat-naar-tokio-aflevering-4', | |
43 | 'ext': 'mp4', | |
44 | 'title': 'Jani gaat naar Tokio - Aflevering 4', | |
7073015a | 45 | 'description': 'md5:2d169e8186ae4247e50c99aaef97f7b2', |
89fd0307 | 46 | }, |
47 | 'params': { | |
89fd0307 | 48 | 'skip_download': True, |
49 | }, | |
50 | 'skip': 'Requires account credentials', | |
51 | }, { | |
7073015a S |
52 | # Requires account credentials but bypassed extraction via v3/embed page |
53 | # without metadata | |
89fd0307 | 54 | 'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839', |
55 | 'info_dict': { | |
56 | 'id': '2674839', | |
57 | 'display_id': 'jani-gaat-naar-tokio-aflevering-4', | |
58 | 'ext': 'mp4', | |
59 | 'title': 'jani-gaat-naar-tokio-aflevering-4', | |
60 | }, | |
61 | 'params': { | |
89fd0307 | 62 | 'skip_download': True, |
63 | }, | |
64 | 'expected_warnings': ['Log in to extract metadata'], | |
9eb4f404 | 65 | }, { |
7073015a S |
66 | # Without video id in URL |
67 | 'url': 'http://www.vier.be/planb/videos/dit-najaar-plan-b', | |
9eb4f404 S |
68 | 'only_matching': True, |
69 | }, { | |
70 | 'url': 'http://www.vier.be/video/v3/embed/16129', | |
71 | 'only_matching': True, | |
72 | }] | |
73 | ||
89fd0307 | 74 | def _real_initialize(self): |
75 | self._logged_in = False | |
76 | ||
77 | def _login(self, site): | |
78 | username, password = self._get_login_info() | |
79 | if username is None or password is None: | |
80 | return | |
81 | ||
82 | login_page = self._download_webpage( | |
83 | 'http://www.%s.be/user/login' % site, | |
84 | None, note='Logging in', errnote='Unable to log in', | |
85 | data=urlencode_postdata({ | |
86 | 'form_id': 'user_login', | |
87 | 'name': username, | |
88 | 'pass': password, | |
89 | }), | |
90 | headers={'Content-Type': 'application/x-www-form-urlencoded'}) | |
91 | ||
92 | login_error = self._html_search_regex( | |
93 | r'(?s)<div class="messages error">\s*<div>\s*<h2.+?</h2>(.+?)<', | |
94 | login_page, 'login error', default=None) | |
95 | if login_error: | |
96 | self.report_warning('Unable to log in: %s' % login_error) | |
97 | else: | |
98 | self._logged_in = True | |
99 | ||
9eb4f404 S |
100 | def _real_extract(self, url): |
101 | mobj = re.match(self._VALID_URL, url) | |
102 | embed_id = mobj.group('embed_id') | |
103 | display_id = mobj.group('display_id') or embed_id | |
89fd0307 | 104 | video_id = mobj.group('id') or embed_id |
a3ba8a7a | 105 | site = mobj.group('site') |
9eb4f404 | 106 | |
89fd0307 | 107 | if not self._logged_in: |
108 | self._login(site) | |
109 | ||
9eb4f404 S |
110 | webpage = self._download_webpage(url, display_id) |
111 | ||
89fd0307 | 112 | if r'id="user-login"' in webpage: |
113 | self.report_warning( | |
114 | 'Log in to extract metadata', video_id=display_id) | |
115 | webpage = self._download_webpage( | |
116 | 'http://www.%s.be/video/v3/embed/%s' % (site, video_id), | |
117 | display_id) | |
118 | ||
9eb4f404 | 119 | video_id = self._search_regex( |
484c9d2d | 120 | [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'], |
7073015a | 121 | webpage, 'video id', default=video_id or display_id) |
9eb4f404 | 122 | application = self._search_regex( |
484c9d2d | 123 | [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'], |
a3ba8a7a | 124 | webpage, 'application', default=site + '_vod') |
9eb4f404 | 125 | filename = self._search_regex( |
484c9d2d S |
126 | [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'], |
127 | webpage, 'filename') | |
9eb4f404 | 128 | |
6ad02195 | 129 | playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename) |
0384932e | 130 | formats = self._extract_wowza_formats(playlist_url, display_id, skip_protocols=['dash']) |
19dbaeec | 131 | self._sort_formats(formats) |
9eb4f404 S |
132 | |
133 | title = self._og_search_title(webpage, default=display_id) | |
134 | description = self._og_search_description(webpage, default=None) | |
135 | thumbnail = self._og_search_thumbnail(webpage, default=None) | |
136 | ||
137 | return { | |
138 | 'id': video_id, | |
139 | 'display_id': display_id, | |
140 | 'title': title, | |
141 | 'description': description, | |
142 | 'thumbnail': thumbnail, | |
143 | 'formats': formats, | |
f58487b3 | 144 | } |
9eb4f404 S |
145 | |
146 | ||
147 | class VierVideosIE(InfoExtractor): | |
148 | IE_NAME = 'vier:videos' | |
a3ba8a7a | 149 | _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)' |
9eb4f404 S |
150 | _TESTS = [{ |
151 | 'url': 'http://www.vier.be/demoestuin/videos', | |
152 | 'info_dict': { | |
153 | 'id': 'demoestuin', | |
154 | }, | |
155 | 'playlist_mincount': 153, | |
a3ba8a7a LV |
156 | }, { |
157 | 'url': 'http://www.vijf.be/temptationisland/videos', | |
158 | 'info_dict': { | |
159 | 'id': 'temptationisland', | |
160 | }, | |
161 | 'playlist_mincount': 159, | |
9eb4f404 S |
162 | }, { |
163 | 'url': 'http://www.vier.be/demoestuin/videos?page=6', | |
164 | 'info_dict': { | |
165 | 'id': 'demoestuin-page6', | |
166 | }, | |
167 | 'playlist_mincount': 20, | |
168 | }, { | |
169 | 'url': 'http://www.vier.be/demoestuin/videos?page=7', | |
170 | 'info_dict': { | |
171 | 'id': 'demoestuin-page7', | |
172 | }, | |
173 | 'playlist_mincount': 13, | |
174 | }] | |
175 | ||
176 | def _real_extract(self, url): | |
177 | mobj = re.match(self._VALID_URL, url) | |
178 | program = mobj.group('program') | |
a3ba8a7a | 179 | site = mobj.group('site') |
9eb4f404 | 180 | |
9eb4f404 S |
181 | page_id = mobj.group('page') |
182 | if page_id: | |
183 | page_id = int(page_id) | |
184 | start_page = page_id | |
9eb4f404 S |
185 | playlist_id = '%s-page%d' % (program, page_id) |
186 | else: | |
187 | start_page = 0 | |
9eb4f404 S |
188 | playlist_id = program |
189 | ||
190 | entries = [] | |
cc1ac110 | 191 | for current_page_id in itertools.count(start_page): |
9eb4f404 | 192 | current_page = self._download_webpage( |
a3ba8a7a | 193 | 'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id), |
9eb4f404 | 194 | program, |
cc1ac110 | 195 | 'Downloading page %d' % (current_page_id + 1)) |
9eb4f404 | 196 | page_entries = [ |
a3ba8a7a | 197 | self.url_result('http://www.' + site + '.be' + video_url, 'Vier') |
9eb4f404 | 198 | for video_url in re.findall( |
a3ba8a7a | 199 | r'<h[23]><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)] |
9eb4f404 | 200 | entries.extend(page_entries) |
cc1ac110 S |
201 | if page_id or '>Meer<' not in current_page: |
202 | break | |
9eb4f404 S |
203 | |
204 | return self.playlist_result(entries, playlist_id) |