youtube_dl/extractor/wdr.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_parse_qs,
   9     compat_urlparse,
  10     determine_ext,
  11     unified_strdate,
  12 )
  13
  14
  15 class WDRIE(InfoExtractor):
  16     _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
  17     _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
  22             'info_dict': {
  23                 'id': 'mdb-362427',
  24                 'ext': 'flv',
  25                 'title': 'Servicezeit',
  26                 'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
  27                 'upload_date': '20140310',
  28             },
  29             'params': {
  30                 'skip_download': True,
  31             },
  32         },
  33         {
  34             'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
  35             'info_dict': {
  36                 'id': 'mdb-363194',
  37                 'ext': 'flv',
  38                 'title': 'Marga Spiegel ist tot',
  39                 'description': 'md5:2309992a6716c347891c045be50992e4',
  40                 'upload_date': '20140311',
  41             },
  42             'params': {
  43                 'skip_download': True,
  44             },
  45         },
  46         {
  47             'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
  48             'md5': '83e9e8fefad36f357278759870805898',
  49             'info_dict': {
  50                 'id': 'mdb-194332',
  51                 'ext': 'mp3',
  52                 'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
  53                 'description': 'md5:2309992a6716c347891c045be50992e4',
  54                 'upload_date': '20091129',
  55             },
  56         },
  57         {
  58             'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
  59             'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
  60             'info_dict': {
  61                 'id': 'mdb-478135',
  62                 'ext': 'mp3',
  63                 'title': 'Flavia Coelho: Amar é Amar',
  64                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
  65                 'upload_date': '20140717',
  66             },
  67         },
  68     ]
  69
  70     def _real_extract(self, url):
  71         mobj = re.match(self._VALID_URL, url)
  72         page_url = mobj.group('url')
  73         page_id = mobj.group('id')
  74
  75         webpage = self._download_webpage(url, page_id)
  76
  77         if mobj.group('player') is None:
  78             entries = [
  79                 self.url_result(page_url + href, 'WDR')
  80                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
  81             ]
  82             return self.playlist_result(entries, page_id)
  83
  84         flashvars = compat_parse_qs(
  85             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
  86
  87         page_id = flashvars['trackerClipId'][0]
  88         video_url = flashvars['dslSrc'][0]
  89         title = flashvars['trackerClipTitle'][0]
  90         thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
  91
  92         if 'trackerClipAirTime' in flashvars:
  93             upload_date = flashvars['trackerClipAirTime'][0]
  94         else:
  95             upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
  96
  97         if upload_date:
  98             upload_date = unified_strdate(upload_date)
  99
 100         if video_url.endswith('.f4m'):
 101             video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
 102             ext = 'flv'
 103         else:
 104             ext = determine_ext(video_url)
 105
 106         description = self._html_search_meta('Description', webpage, 'description')
 107
 108         return {
 109             'id': page_id,
 110             'url': video_url,
 111             'ext': ext,
 112             'title': title,
 113             'description': description,
 114             'thumbnail': thumbnail,
 115             'upload_date': upload_date,
 116         }
 117
 118
 119 class WDRMobileIE(InfoExtractor):
 120     _VALID_URL = r'''(?x)
 121         https?://mobile-ondemand\.wdr\.de/
 122         .*?/fsk(?P<age_limit>[0-9]+)
 123         /[0-9]+/[0-9]+/
 124         (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
 125     IE_NAME = 'wdr:mobile'
 126     _TEST = {
 127         'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
 128         'info_dict': {
 129             'title': '4283021',
 130             'id': '421735',
 131             'ext': 'mp4',
 132             'age_limit': 0,
 133         },
 134         'skip': 'Problems with loading data.'
 135     }
 136
 137     def _real_extract(self, url):
 138         mobj = re.match(self._VALID_URL, url)
 139         return {
 140             'id': mobj.group('id'),
 141             'title': mobj.group('title'),
 142             'age_limit': int(mobj.group('age_limit')),
 143             'url': url,
 144             'ext': determine_ext(url),
 145             'user_agent': 'mobile',
 146         }
 147
 148
 149 class WDRMausIE(InfoExtractor):
 150     _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
 151     IE_DESC = 'Sendung mit der Maus'
 152     _TESTS = [{
 153         'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
 154         'info_dict': {
 155             'id': 'aktuelle-sendung',
 156             'ext': 'mp4',
 157             'thumbnail': 're:^http://.+\.jpg',
 158             'upload_date': 're:^[0-9]{8}$',
 159             'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
 160         }
 161     }, {
 162         'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
 163         'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
 164         'info_dict': {
 165             'id': '40_jahre_maus',
 166             'ext': 'mp4',
 167             'thumbnail': 're:^http://.+\.jpg',
 168             'upload_date': '20131007',
 169             'title': '12.03.2011 - 40 Jahre Maus',
 170         }
 171     }]
 172
 173     def _real_extract(self, url):
 174         mobj = re.match(self._VALID_URL, url)
 175         video_id = mobj.group('id')
 176
 177         webpage = self._download_webpage(url, video_id)
 178         param_code = self._html_search_regex(
 179             r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')
 180
 181         title_date = self._search_regex(
 182             r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
 183             webpage, 'air date')
 184         title_str = self._html_search_regex(
 185             r'<h1>(.*?)</h1>', webpage, 'title')
 186         title = '%s - %s' % (title_date, title_str)
 187         upload_date = unified_strdate(
 188             self._html_search_meta('dc.date', webpage))
 189
 190         fields = compat_parse_qs(param_code)
 191         video_url = fields['firstVideo'][0]
 192         thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
 193
 194         formats = [{
 195             'format_id': 'rtmp',
 196             'url': video_url,
 197         }]
 198
 199         jscode = self._download_webpage(
 200             'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
 201             video_id, fatal=False,
 202             note='Downloading URL translation table',
 203             errnote='Could not download URL translation table')
 204         if jscode:
 205             for m in re.finditer(
 206                     r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
 207                     jscode):
 208                 if video_url.startswith(m.group('stream')):
 209                     http_url = video_url.replace(
 210                         m.group('stream'), m.group('dl'))
 211                     formats.append({
 212                         'format_id': 'http',
 213                         'url': http_url,
 214                     })
 215                     break
 216
 217         self._sort_formats(formats)
 218
 219         return {
 220             'id': video_id,
 221             'title': title,
 222             'formats': formats,
 223             'thumbnail': thumbnail,
 224             'upload_date': upload_date,
 225         }
 226
 227 # TODO test _1