Raphaël G. Git Repositories - youtubedl/blob - 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             'info_dict': {
  75                 'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
  76             }
  77         }
  78     ]
  79
  80     def _real_extract(self, url):
  81         mobj = re.match(self._VALID_URL, url)
  82         page_url = mobj.group('url')
  83         page_id = mobj.group('id')
  84
  85         webpage = self._download_webpage(url, page_id)
  86
  87         if mobj.group('player') is None:
  88             entries = [
  89                 self.url_result(page_url + href, 'WDR')
  90                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
  91             ]
  92
  93             if entries:  # Playlist page
  94                 return self.playlist_result(entries, page_id)
  95
  96             # Overview page
  97             entries = []
  98             for page_num in itertools.count(2):
  99                 hrefs = re.findall(
 100                     r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
 101                     webpage)
 102                 entries.extend(
 103                     self.url_result(page_url + href, 'WDR')
 104                     for href in hrefs)
 105                 next_url_m = re.search(
 106                     r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
 107                 if not next_url_m:
 108                     break
 109                 next_url = page_url + next_url_m.group(1)
 110                 webpage = self._download_webpage(
 111                     next_url, page_id,
 112                     note='Downloading playlist page %d' % page_num)
 113             return self.playlist_result(entries, page_id)
 114
 115         flashvars = compat_parse_qs(
 116             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
 117
 118         page_id = flashvars['trackerClipId'][0]
 119         video_url = flashvars['dslSrc'][0]
 120         title = flashvars['trackerClipTitle'][0]
 121         thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
 122
 123         if 'trackerClipAirTime' in flashvars:
 124             upload_date = flashvars['trackerClipAirTime'][0]
 125         else:
 126             upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
 127
 128         if upload_date:
 129             upload_date = unified_strdate(upload_date)
 130
 131         if video_url.endswith('.f4m'):
 132             video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
 133             ext = 'flv'
 134         else:
 135             ext = determine_ext(video_url)
 136
 137         description = self._html_search_meta('Description', webpage, 'description')
 138
 139         return {
 140             'id': page_id,
 141             'url': video_url,
 142             'ext': ext,
 143             'title': title,
 144             'description': description,
 145             'thumbnail': thumbnail,
 146             'upload_date': upload_date,
 147         }
 148
 149
 150 class WDRMobileIE(InfoExtractor):
 151     _VALID_URL = r'''(?x)
 152         https?://mobile-ondemand\.wdr\.de/
 153         .*?/fsk(?P<age_limit>[0-9]+)
 154         /[0-9]+/[0-9]+/
 155         (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
 156     IE_NAME = 'wdr:mobile'
 157     _TEST = {
 158         'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
 159         'info_dict': {
 160             'title': '4283021',
 161             'id': '421735',
 162             'ext': 'mp4',
 163             'age_limit': 0,
 164         },
 165         'skip': 'Problems with loading data.'
 166     }
 167
 168     def _real_extract(self, url):
 169         mobj = re.match(self._VALID_URL, url)
 170         return {
 171             'id': mobj.group('id'),
 172             'title': mobj.group('title'),
 173             'age_limit': int(mobj.group('age_limit')),
 174             'url': url,
 175             'http_headers': {
 176                 'User-Agent': 'mobile',
 177             },
 178         }
 179
 180
 181 class WDRMausIE(InfoExtractor):
 182     _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
 183     IE_DESC = 'Sendung mit der Maus'
 184     _TESTS = [{
 185         'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
 186         'info_dict': {
 187             'id': 'aktuelle-sendung',
 188             'ext': 'mp4',
 189             'thumbnail': 're:^http://.+\.jpg',
 190             'upload_date': 're:^[0-9]{8}$',
 191             'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
 192         }
 193     }, {
 194         'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
 195         'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
 196         'info_dict': {
 197             'id': '40_jahre_maus',
 198             'ext': 'mp4',
 199             'thumbnail': 're:^http://.+\.jpg',
 200             'upload_date': '20131007',
 201             'title': '12.03.2011 - 40 Jahre Maus',
 202         }
 203     }]
 204
 205     def _real_extract(self, url):
 206         video_id = self._match_id(url)
 207
 208         webpage = self._download_webpage(url, video_id)
 209         param_code = self._html_search_regex(
 210             r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
 211
 212         title_date = self._search_regex(
 213             r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
 214             webpage, 'air date')
 215         title_str = self._html_search_regex(
 216             r'<h1>(.*?)</h1>', webpage, 'title')
 217         title = '%s - %s' % (title_date, title_str)
 218         upload_date = unified_strdate(
 219             self._html_search_meta('dc.date', webpage))
 220
 221         fields = compat_parse_qs(param_code)
 222         video_url = fields['firstVideo'][0]
 223         thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
 224
 225         formats = [{
 226             'format_id': 'rtmp',
 227             'url': video_url,
 228         }]
 229
 230         jscode = self._download_webpage(
 231             'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
 232             video_id, fatal=False,
 233             note='Downloading URL translation table',
 234             errnote='Could not download URL translation table')
 235         if jscode:
 236             for m in re.finditer(
 237                     r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
 238                     jscode):
 239                 if video_url.startswith(m.group('stream')):
 240                     http_url = video_url.replace(
 241                         m.group('stream'), m.group('dl'))
 242                     formats.append({
 243                         'format_id': 'http',
 244                         'url': http_url,
 245                     })
 246                     break
 247
 248         self._sort_formats(formats)
 249
 250         return {
 251             'id': video_id,
 252             'title': title,
 253             'formats': formats,
 254             'thumbnail': thumbnail,
 255             'upload_date': upload_date,
 256         }