Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/wdr.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_urlparse,
   9     determine_ext,
  10     unified_strdate,
  11 )
  12
  13
  14 class WDRIE(InfoExtractor):
  15     _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
  16     _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
  17
  18     _TESTS = [
  19         {
  20             'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
  21             'info_dict': {
  22                 'id': 'mdb-362427',
  23                 'ext': 'flv',
  24                 'title': 'Servicezeit',
  25                 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
  26                 'upload_date': '20140310',
  27             },
  28             'params': {
  29                 'skip_download': True,
  30             },
  31         },
  32         {
  33             'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
  34             'info_dict': {
  35                 'id': 'mdb-363194',
  36                 'ext': 'flv',
  37                 'title': 'Marga Spiegel ist tot',
  38                 'description': 'md5:2309992a6716c347891c045be50992e4',
  39                 'upload_date': '20140311',
  40             },
  41             'params': {
  42                 'skip_download': True,
  43             },
  44         },
  45         {
  46             'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
  47             'md5': '83e9e8fefad36f357278759870805898',
  48             'info_dict': {
  49                 'id': 'mdb-194332',
  50                 'ext': 'mp3',
  51                 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
  52                 'description': 'md5:2309992a6716c347891c045be50992e4',
  53                 'upload_date': '20091129',
  54             },
  55         },
  56         {
  57             'url': 'http://www.funkhauseuropa.de/av/audiogrenzenlosleckerbaklava101-audioplayer.html',
  58             'md5': 'cfff440d4ee64114083ac44676df5d15',
  59             'info_dict': {
  60                 'id': 'mdb-363068',
  61                 'ext': 'mp3',
  62                 'title': 'Grenzenlos lecker - Baklava',
  63                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
  64                 'upload_date': '20140311',
  65             },
  66         },
  67     ]
  68
  69     def _real_extract(self, url):
  70         mobj = re.match(self._VALID_URL, url)
  71         page_url = mobj.group('url')
  72         page_id = mobj.group('id')
  73
  74         webpage = self._download_webpage(url, page_id)
  75
  76         if mobj.group('player') is None:
  77             entries = [
  78                 self.url_result(page_url + href, 'WDR')
  79                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
  80             ]
  81             return self.playlist_result(entries, page_id)
  82
  83         flashvars = compat_urlparse.parse_qs(
  84             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
  85
  86         page_id = flashvars['trackerClipId'][0]
  87         video_url = flashvars['dslSrc'][0]
  88         title = flashvars['trackerClipTitle'][0]
  89         thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
  90
  91         if 'trackerClipAirTime' in flashvars:
  92             upload_date = flashvars['trackerClipAirTime'][0]
  93         else:
  94             upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
  95
  96         if upload_date:
  97             upload_date = unified_strdate(upload_date)
  98
  99         if video_url.endswith('.f4m'):
 100             video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
 101             ext = 'flv'
 102         else:
 103             ext = determine_ext(video_url)
 104
 105         description = self._html_search_meta('Description', webpage, 'description')
 106
 107         return {
 108             'id': page_id,
 109             'url': video_url,
 110             'ext': ext,
 111             'title': title,
 112             'description': description,
 113             'thumbnail': thumbnail,
 114             'upload_date': upload_date,
 115         }
 116
 117
 118 class WDRMobileIE(InfoExtractor):
 119     _VALID_URL = r'''(?x)
 120         https?://mobile-ondemand\.wdr\.de/
 121         .*?/fsk(?P<age_limit>[0-9]+)
 122         /[0-9]+/[0-9]+/
 123         (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
 124     IE_NAME = 'wdr:mobile'
 125     _TEST = {
 126         'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
 127         'info_dict': {
 128             'title': '4283021',
 129             'id': '421735',
 130             'age_limit': 0,
 131         },
 132         '_skip': 'Will be depublicized shortly'
 133     }
 134
 135     def _real_extract(self, url):
 136         mobj = re.match(self._VALID_URL, url)
 137         return {
 138             'id': mobj.group('id'),
 139             'title': mobj.group('title'),
 140             'age_limit': int(mobj.group('age_limit')),
 141             'url': url,
 142             'user_agent': 'mobile',
 143         }
 144
 145
 146 class WDRMausIE(InfoExtractor):
 147     _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
 148     IE_DESC = 'Sendung mit der Maus'
 149     _TESTS = [{
 150         'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
 151         'info_dict': {
 152             'id': 'aktuelle-sendung',
 153             'ext': 'mp4',
 154             'thumbnail': 're:^http://.+\.jpg',
 155             'upload_date': 're:^[0-9]{8}$',
 156             'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
 157         }
 158     }, {
 159         'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
 160         'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
 161         'info_dict': {
 162             'id': '40_jahre_maus',
 163             'ext': 'mp4',
 164             'thumbnail': 're:^http://.+\.jpg',
 165             'upload_date': '20131007',
 166             'title': '12.03.2011 - 40 Jahre Maus',
 167         }
 168     }]
 169
 170     def _real_extract(self, url):
 171         mobj = re.match(self._VALID_URL, url)
 172         video_id = mobj.group('id')
 173
 174         webpage = self._download_webpage(url, video_id)
 175         param_code = self._html_search_regex(
 176             r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
 177
 178         title_date = self._search_regex(
 179             r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
 180             webpage, 'air date')
 181         title_str = self._html_search_regex(
 182             r'<h1>(.*?)</h1>', webpage, 'title')
 183         title = '%s - %s' % (title_date, title_str)
 184         upload_date = unified_strdate(
 185             self._html_search_meta('dc.date', webpage))
 186
 187         fields = compat_parse_qs(param_code)
 188         video_url = fields['firstVideo'][0]
 189         thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
 190
 191         formats = [{
 192             'format_id': 'rtmp',
 193             'url': video_url,
 194         }]
 195
 196         jscode = self._download_webpage(
 197             'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
 198             video_id, fatal=False,
 199             note='Downloading URL translation table',
 200             errnote='Could not download URL translation table')
 201         if jscode:
 202             for m in re.finditer(
 203                     r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
 204                     jscode):
 205                 if video_url.startswith(m.group('stream')):
 206                     http_url = video_url.replace(
 207                         m.group('stream'), m.group('dl'))
 208                     formats.append({
 209                         'format_id': 'http',
 210                         'url': http_url,
 211                     })
 212                     break
 213
 214         self._sort_formats(formats)
 215
 216         return {
 217             'id': video_id,
 218             'title': title,
 219             'formats': formats,
 220             'thumbnail': thumbnail,
 221             'upload_date': upload_date,
 222         }
 223
 224 # TODO test _1