_ Git - youtube-dl/blob - 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, ExtractorError
   8
   9
  10 class TagesschauIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/(ts|tsg|tt|nm)|video/video|tsvorzwanzig)(?P<id>-?[0-9]+)\.html'
  12
  13     _TESTS = [{
  14         'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
  15         'md5': 'bcdeac2194fb296d599ce7929dfa4009',
  16         'info_dict': {
  17             'id': '1399128',
  18             'ext': 'mp4',
  19             'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen',
  20             'description': 'md5:69da3c61275b426426d711bde96463ab',
  21             'thumbnail': 're:^http:.*\.jpg$',
  22         },
  23     }, {
  24         'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
  25         'md5': '3c54c1f6243d279b706bde660ceec633',
  26         'info_dict': {
  27             'id': '5727',
  28             'ext': 'mp4',
  29             'description': 'md5:695c01bfd98b7e313c501386327aea59',
  30             'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
  31             'thumbnail': 're:^http:.*\.jpg$',
  32         }
  33     }, {
  34         'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
  35         'md5': '90757268b49ef56deae90c7b48928d58',
  36         'info_dict': {
  37             'id': '3771',
  38             'ext': 'mp4',
  39             'description': '',
  40             'title': 'Sendung: tagesschau (mit Gebärdensprache) \t14.07.2015 20:00 Uhr',
  41             'thumbnail': 're:^http:.*\.jpg$',
  42         }
  43     }, {
  44         'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
  45         'md5': '6e3ebdc75e8d67da966a8d06721eda71',
  46         'info_dict': {
  47             'id': '3827',
  48             'ext': 'mp4',
  49             'description': 'md5:d511d0e278b0ad341a95ad9ab992ce66',
  50             'title': 'Sendung: tagesthemen \t14.07.2015 22:15 Uhr',
  51             'thumbnail': 're:^http:.*\.jpg$',
  52         }
  53     }, {
  54         'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
  55         'md5': '8a8875a568f0a5ae5ceef93c501a225f',
  56         'info_dict': {
  57             'id': '3475',
  58             'ext': 'mp4',
  59             'description': 'md5:ed149f5649cda3dac86813a9d777e131',
  60             'title': 'Sendung: nachtmagazin \t15.07.2015 00:15 Uhr',
  61             'thumbnail': 're:^http:.*\.jpg$',
  62         }
  63     }, {
  64         'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
  65         'md5': 'be4d6f0421f2acd8abe25ea29f6f015b',
  66         'info_dict': {
  67             'id': '959',
  68             'ext': 'mp4',
  69             'description': '',
  70             'title': 'Sendung: tagesschau vor 20 Jahren \t14.07.2015 22:45 Uhr',
  71             'thumbnail': 're:^http:.*\.jpg$',
  72         }
  73     }]
  74
  75     _FORMATS = {
  76         's': {'width': 256, 'height': 144, 'quality': 1},
  77         'm': {'width': 512, 'height': 288, 'quality': 2},
  78         'l': {'width': 960, 'height': 544, 'quality': 3},
  79     }
  80
  81     def _real_extract(self, url):
  82         video_id = self._match_id(url)
  83         display_id = video_id.lstrip('-')
  84         webpage = self._download_webpage(url, display_id)
  85
  86         player_url = self._html_search_meta(
  87             'twitter:player', webpage, 'player URL', default=None)
  88         if player_url:
  89             playerpage = self._download_webpage(
  90                 player_url, display_id, 'Downloading player page')
  91
  92             medias = re.findall(
  93                 r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"',
  94                 playerpage)
  95             formats = []
  96             for url, ext, res in medias:
  97                 f = {
  98                     'format_id': res + '_' + ext,
  99                     'url': url,
 100                     'ext': ext,
 101                 }
 102                 f.update(self._FORMATS.get(res, {}))
 103                 formats.append(f)
 104             thumbnail_fn = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
 105             title = self._og_search_title(webpage).strip()
 106             description = self._og_search_description(webpage).strip()
 107         else:
 108             download_text = self._search_regex(
 109                 r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>',
 110                 webpage, 'download links')
 111             links = re.finditer(
 112                 r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
 113                 download_text)
 114             formats = []
 115             for l in links:
 116                 format_id = self._search_regex(
 117                     r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
 118                 format = {
 119                     'format_id': format_id,
 120                     'url': l.group('url'),
 121                     'format_name': l.group('name'),
 122                 }
 123                 m = re.match(
 124                     r'''(?x)
 125                         Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
 126                         (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
 127                         (?P<vbr>[0-9]+)kbps&\#10;
 128                         Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
 129                         Gr&ouml;&szlig;e:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
 130                     l.group('title'))
 131                 if m:
 132                     format.update({
 133                         'format_note': m.group('audio_desc'),
 134                         'vcodec': m.group('vcodec'),
 135                         'width': int(m.group('width')),
 136                         'height': int(m.group('height')),
 137                         'abr': int(m.group('abr')),
 138                         'vbr': int(m.group('vbr')),
 139                         'filesize_approx': parse_filesize(m.group('filesize_approx')),
 140                     })
 141                 formats.append(format)
 142             thumbnail_fn = self._search_regex(
 143                 r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"',
 144                 webpage, 'thumbnail', fatal=False)
 145             # there are some videos without description
 146             description = ""
 147             try:
 148                 description = self._html_search_regex(
 149                     r'(?s)<p class="teasertext">(.*?)</p>',
 150                     webpage, 'description', fatal=False)
 151             except ExtractorError:
 152                 pass
 153             title = self._html_search_regex(
 154                 r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
 155
 156         self._sort_formats(formats)
 157         thumbnail = 'http://www.tagesschau.de' + thumbnail_fn
 158
 159         return {
 160             'id': display_id,
 161             'title': title,
 162             'thumbnail': thumbnail,
 163             'formats': formats,
 164             'description': description,
 165         }