youtube_dl/extractor/tagesschau.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 parse_filesize
   8
   9
  10 class TagesschauIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)(?:~_?[^/#?]+?)?\.html'
  12
  13     _TESTS = [{
  14         'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
  15         'md5': '917a228bc7df7850783bc47979673a09',
  16         'info_dict': {
  17             'id': '102143',
  18             'ext': 'mp4',
  19             'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
  20             'description': 'md5:171feccd9d9b3dd54d05d501568f6359',
  21             'thumbnail': 're:^https?:.*\.jpg$',
  22         },
  23     }, {
  24         'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
  25         'md5': '3c54c1f6243d279b706bde660ceec633',
  26         'info_dict': {
  27             'id': '5727',
  28             'ext': 'mp4',
  29             'description': 'md5:695c01bfd98b7e313c501386327aea59',
  30             'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
  31             'thumbnail': 're:^https?:.*\.jpg$',
  32         },
  33     }, {
  34         'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html',
  35         'md5': 'aef45de271c4bf0a5db834aa40bf774c',
  36         'info_dict': {
  37             'id': '18407',
  38             'ext': 'mp3',
  39             'title': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
  40             'description': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
  41             'thumbnail': 're:^https?:.*\.jpg$',
  42         },
  43     }, {
  44         'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
  45         'only_matching': True,
  46     }, {
  47         'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
  48         'only_matching': True,
  49     }, {
  50         'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
  51         'only_matching': True,
  52     }, {
  53         'url': 'http://www.tagesschau.de/multimedia/sendung/weltspiegel-3167.html',
  54         'only_matching': True,
  55     }, {
  56         'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
  57         'only_matching': True,
  58     }, {
  59         'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html',
  60         'only_matching': True,
  61     }, {
  62         'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
  63         'only_matching': True,
  64     }, {
  65         'url': 'http://www.tagesschau.de/multimedia/video/video-179517~player.html',
  66         'only_matching': True,
  67     }]
  68
  69     _FORMATS = {
  70         'xs': {'quality': 0},
  71         's': {'width': 320, 'height': 180, 'quality': 1},
  72         'm': {'width': 512, 'height': 288, 'quality': 2},
  73         'l': {'width': 960, 'height': 540, 'quality': 3},
  74         'xl': {'width': 1280, 'height': 720, 'quality': 4},
  75         'xxl': {'quality': 5},
  76     }
  77
  78     def _real_extract(self, url):
  79         video_id = self._match_id(url)
  80         display_id = video_id.lstrip('-')
  81         webpage = self._download_webpage(url, display_id)
  82
  83         player_url = self._html_search_meta(
  84             'twitter:player', webpage, 'player URL', default=None)
  85         if player_url:
  86             playerpage = self._download_webpage(
  87                 player_url, display_id, 'Downloading player page')
  88
  89             formats = []
  90             for media in re.finditer(
  91                     r'''(?x)
  92                         (?P<q_url>["\'])(?P<url>http://media.+?)(?P=q_url)
  93                         ,\s*type:(?P<q_type>["\'])(?P<type>video|audio)/(?P<ext>.+?)(?P=q_type)
  94                         (?:,\s*quality:(?P<q_quality>["\'])(?P<quality>.+?)(?P=q_quality))?
  95                     ''', playerpage):
  96                 url = media.group('url')
  97                 type_ = media.group('type')
  98                 ext = media.group('ext')
  99                 res = media.group('quality')
 100                 f = {
 101                     'format_id': '%s_%s' % (res, ext) if res else ext,
 102                     'url': url,
 103                     'ext': ext,
 104                     'vcodec': 'none' if type_ == 'audio' else None,
 105                 }
 106                 f.update(self._FORMATS.get(res, {}))
 107                 formats.append(f)
 108             thumbnail = self._og_search_thumbnail(playerpage)
 109             title = self._og_search_title(webpage).strip()
 110             description = self._og_search_description(webpage).strip()
 111         else:
 112             download_text = self._search_regex(
 113                 r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>',
 114                 webpage, 'download links')
 115             links = re.finditer(
 116                 r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
 117                 download_text)
 118             formats = []
 119             for l in links:
 120                 format_id = self._search_regex(
 121                     r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
 122                 format = {
 123                     'format_id': format_id,
 124                     'url': l.group('url'),
 125                     'format_name': l.group('name'),
 126                 }
 127                 m = re.match(
 128                     r'''(?x)
 129                         Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
 130                         (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
 131                         (?P<vbr>[0-9]+)kbps&\#10;
 132                         Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
 133                         Gr&ouml;&szlig;e:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
 134                     l.group('title'))
 135                 if m:
 136                     format.update({
 137                         'format_note': m.group('audio_desc'),
 138                         'vcodec': m.group('vcodec'),
 139                         'width': int(m.group('width')),
 140                         'height': int(m.group('height')),
 141                         'abr': int(m.group('abr')),
 142                         'vbr': int(m.group('vbr')),
 143                         'filesize_approx': parse_filesize(m.group('filesize_approx')),
 144                     })
 145                 formats.append(format)
 146             thumbnail = self._og_search_thumbnail(webpage)
 147             description = self._html_search_regex(
 148                 r'(?s)<p class="teasertext">(.*?)</p>',
 149                 webpage, 'description', default=None)
 150             title = self._html_search_regex(
 151                 r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
 152
 153         self._sort_formats(formats)
 154
 155         return {
 156             'id': display_id,
 157             'title': title,
 158             'thumbnail': thumbnail,
 159             'formats': formats,
 160             'description': description,
 161         }