[wdr] Support overviews (Fixes #4651)
[ytdl] / youtube_dl / extractor / wdr.py
1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
3
4 import itertools
5 import re
6
7 from .common import InfoExtractor
8 from ..compat import (
9     compat_parse_qs,
10     compat_urlparse,
11 )
12 from ..utils import (
13     determine_ext,
14     unified_strdate,
15 )
16
17
18 class WDRIE(InfoExtractor):
19     _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
20     _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
21
22     _TESTS = [
23         {
24             'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
25             'info_dict': {
26                 'id': 'mdb-362427',
27                 'ext': 'flv',
28                 'title': 'Servicezeit',
29                 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
30                 'upload_date': '20140310',
31             },
32             'params': {
33                 'skip_download': True,
34             },
35         },
36         {
37             'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
38             'info_dict': {
39                 'id': 'mdb-363194',
40                 'ext': 'flv',
41                 'title': 'Marga Spiegel ist tot',
42                 'description': 'md5:2309992a6716c347891c045be50992e4',
43                 'upload_date': '20140311',
44             },
45             'params': {
46                 'skip_download': True,
47             },
48         },
49         {
50             'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
51             'md5': '83e9e8fefad36f357278759870805898',
52             'info_dict': {
53                 'id': 'mdb-194332',
54                 'ext': 'mp3',
55                 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
56                 'description': 'md5:2309992a6716c347891c045be50992e4',
57                 'upload_date': '20091129',
58             },
59         },
60         {
61             'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
62             'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
63             'info_dict': {
64                 'id': 'mdb-478135',
65                 'ext': 'mp3',
66                 'title': 'Flavia Coelho: Amar é Amar',
67                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
68                 'upload_date': '20140717',
69             },
70         },
71         {
72             'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
73             'playlist_mincount': 146,
74         }
75     ]
76
77     def _real_extract(self, url):
78         mobj = re.match(self._VALID_URL, url)
79         page_url = mobj.group('url')
80         page_id = mobj.group('id')
81
82         webpage = self._download_webpage(url, page_id)
83
84         if mobj.group('player') is None:
85             entries = [
86                 self.url_result(page_url + href, 'WDR')
87                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
88             ]
89
90             if entries:  # Playlist page
91                 return self.playlist_result(entries, page_id)
92
93             # Overview page
94             entries = []
95             for page_num in itertools.count(2):
96                 hrefs = re.findall(
97                     r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
98                     webpage)
99                 entries.extend(
100                     self.url_result(page_url + href, 'WDR')
101                     for href in hrefs)
102                 next_url_m = re.search(
103                     r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
104                 if not next_url_m:
105                     break
106                 next_url = page_url + next_url_m.group(1)
107                 webpage = self._download_webpage(
108                     next_url, page_id,
109                     note='Downloading playlist page %d' % page_num)
110             return self.playlist_result(entries, page_id)
111
112         flashvars = compat_parse_qs(
113             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
114
115         page_id = flashvars['trackerClipId'][0]
116         video_url = flashvars['dslSrc'][0]
117         title = flashvars['trackerClipTitle'][0]
118         thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
119
120         if 'trackerClipAirTime' in flashvars:
121             upload_date = flashvars['trackerClipAirTime'][0]
122         else:
123             upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
124
125         if upload_date:
126             upload_date = unified_strdate(upload_date)
127
128         if video_url.endswith('.f4m'):
129             video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
130             ext = 'flv'
131         else:
132             ext = determine_ext(video_url)
133
134         description = self._html_search_meta('Description', webpage, 'description')
135
136         return {
137             'id': page_id,
138             'url': video_url,
139             'ext': ext,
140             'title': title,
141             'description': description,
142             'thumbnail': thumbnail,
143             'upload_date': upload_date,
144         }
145
146
147 class WDRMobileIE(InfoExtractor):
148     _VALID_URL = r'''(?x)
149         https?://mobile-ondemand\.wdr\.de/
150         .*?/fsk(?P<age_limit>[0-9]+)
151         /[0-9]+/[0-9]+/
152         (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
153     IE_NAME = 'wdr:mobile'
154     _TEST = {
155         'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
156         'info_dict': {
157             'title': '4283021',
158             'id': '421735',
159             'ext': 'mp4',
160             'age_limit': 0,
161         },
162         'skip': 'Problems with loading data.'
163     }
164
165     def _real_extract(self, url):
166         mobj = re.match(self._VALID_URL, url)
167         return {
168             'id': mobj.group('id'),
169             'title': mobj.group('title'),
170             'age_limit': int(mobj.group('age_limit')),
171             'url': url,
172             'user_agent': 'mobile',
173         }
174
175
176 class WDRMausIE(InfoExtractor):
177     _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
178     IE_DESC = 'Sendung mit der Maus'
179     _TESTS = [{
180         'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
181         'info_dict': {
182             'id': 'aktuelle-sendung',
183             'ext': 'mp4',
184             'thumbnail': 're:^http://.+\.jpg',
185             'upload_date': 're:^[0-9]{8}$',
186             'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
187         }
188     }, {
189         'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
190         'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
191         'info_dict': {
192             'id': '40_jahre_maus',
193             'ext': 'mp4',
194             'thumbnail': 're:^http://.+\.jpg',
195             'upload_date': '20131007',
196             'title': '12.03.2011 - 40 Jahre Maus',
197         }
198     }]
199
200     def _real_extract(self, url):
201         video_id = self._match_id(url)
202
203         webpage = self._download_webpage(url, video_id)
204         param_code = self._html_search_regex(
205             r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
206
207         title_date = self._search_regex(
208             r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
209             webpage, 'air date')
210         title_str = self._html_search_regex(
211             r'<h1>(.*?)</h1>', webpage, 'title')
212         title = '%s - %s' % (title_date, title_str)
213         upload_date = unified_strdate(
214             self._html_search_meta('dc.date', webpage))
215
216         fields = compat_parse_qs(param_code)
217         video_url = fields['firstVideo'][0]
218         thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
219
220         formats = [{
221             'format_id': 'rtmp',
222             'url': video_url,
223         }]
224
225         jscode = self._download_webpage(
226             'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
227             video_id, fatal=False,
228             note='Downloading URL translation table',
229             errnote='Could not download URL translation table')
230         if jscode:
231             for m in re.finditer(
232                     r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
233                     jscode):
234                 if video_url.startswith(m.group('stream')):
235                     http_url = video_url.replace(
236                         m.group('stream'), m.group('dl'))
237                     formats.append({
238                         'format_id': 'http',
239                         'url': http_url,
240                     })
241                     break
242
243         self._sort_formats(formats)
244
245         return {
246             'id': video_id,
247             'title': title,
248             'formats': formats,
249             'thumbnail': thumbnail,
250             'upload_date': upload_date,
251         }