Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/spiegel.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .nexx import (
   8     NexxIE,
   9     NexxEmbedIE,
  10 )
  11 from .spiegeltv import SpiegeltvIE
  12 from ..compat import compat_urlparse
  13 from ..utils import (
  14     extract_attributes,
  15     unified_strdate,
  16     get_element_by_attribute,
  17 )
  18
  19
  20 class SpiegelIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$'
  22     _TESTS = [{
  23         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
  24         'md5': '2c2754212136f35fb4b19767d242f66e',
  25         'info_dict': {
  26             'id': '1259285',
  27             'ext': 'mp4',
  28             'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
  29             'description': 'md5:8029d8310232196eb235d27575a8b9f4',
  30             'duration': 49,
  31             'upload_date': '20130311',
  32         },
  33     }, {
  34         'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
  35         'md5': 'f2cdf638d7aa47654e251e1aee360af1',
  36         'info_dict': {
  37             'id': '1309159',
  38             'ext': 'mp4',
  39             'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
  40             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
  41             'duration': 983,
  42             'upload_date': '20131115',
  43         },
  44     }, {
  45         'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
  46         'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51',
  47         'info_dict': {
  48             'id': '1519126',
  49             'ext': 'mp4',
  50             'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
  51             'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
  52             'upload_date': '20140904',
  53         }
  54     }, {
  55         'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
  56         'only_matching': True,
  57     }, {
  58         # nexx video
  59         'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
  60         'only_matching': True,
  61     }]
  62
  63     def _real_extract(self, url):
  64         video_id = self._match_id(url)
  65         webpage, handle = self._download_webpage_handle(url, video_id)
  66
  67         # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
  68         if SpiegeltvIE.suitable(handle.geturl()):
  69             return self.url_result(handle.geturl(), 'Spiegeltv')
  70
  71         nexx_id = self._search_regex(
  72             r'nexxOmniaId\s*:\s*(\d+)', webpage, 'nexx id', default=None)
  73         if nexx_id:
  74             domain_id = NexxIE._extract_domain_id(webpage) or '748'
  75             return self.url_result(
  76                 'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(),
  77                 video_id=nexx_id)
  78
  79         video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default=''))
  80
  81         title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage)
  82         description = video_data.get('data-video-teaser') or self._html_search_meta('description', webpage, 'description')
  83
  84         base_url = self._search_regex(
  85             [r'server\s*:\s*(["\'])(?P<url>.+?)\1', r'var\s+server\s*=\s*"(?P<url>[^"]+)\"'],
  86             webpage, 'server URL', group='url')
  87
  88         xml_url = base_url + video_id + '.xml'
  89         idoc = self._download_xml(xml_url, video_id)
  90
  91         formats = []
  92         for n in list(idoc):
  93             if n.tag.startswith('type') and n.tag != 'type6':
  94                 format_id = n.tag.rpartition('type')[2]
  95                 video_url = base_url + n.find('./filename').text
  96                 formats.append({
  97                     'format_id': format_id,
  98                     'url': video_url,
  99                     'width': int(n.find('./width').text),
 100                     'height': int(n.find('./height').text),
 101                     'abr': int(n.find('./audiobitrate').text),
 102                     'vbr': int(n.find('./videobitrate').text),
 103                     'vcodec': n.find('./codec').text,
 104                     'acodec': 'MP4A',
 105                 })
 106         duration = float(idoc[0].findall('./duration')[0].text)
 107
 108         self._check_formats(formats, video_id)
 109         self._sort_formats(formats)
 110
 111         return {
 112             'id': video_id,
 113             'title': title,
 114             'description': description.strip() if description else None,
 115             'duration': duration,
 116             'upload_date': unified_strdate(video_data.get('data-video-date')),
 117             'formats': formats,
 118         }
 119
 120
 121 class SpiegelArticleIE(InfoExtractor):
 122     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
 123     IE_NAME = 'Spiegel:Article'
 124     IE_DESC = 'Articles on spiegel.de'
 125     _TESTS = [{
 126         'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
 127         'info_dict': {
 128             'id': '1516455',
 129             'ext': 'mp4',
 130             'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
 131             'description': 're:^Patrick Kämnitz gehört.{100,}',
 132             'upload_date': '20140825',
 133         },
 134     }, {
 135         'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
 136         'info_dict': {
 137
 138         },
 139         'playlist_count': 6,
 140     }, {
 141         # Nexx iFrame embed
 142         'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html',
 143         'info_dict': {
 144             'id': '161464',
 145             'ext': 'mp4',
 146             'title': 'Nervenkitzel Achterbahn',
 147             'alt_title': 'Karussellbauer in Deutschland',
 148             'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
 149             'release_year': 2005,
 150             'creator': 'SPIEGEL TV',
 151             'thumbnail': r're:^https?://.*\.jpg$',
 152             'duration': 2761,
 153             'timestamp': 1394021479,
 154             'upload_date': '20140305',
 155         },
 156         'params': {
 157             'format': 'bestvideo',
 158             'skip_download': True,
 159         },
 160     }]
 161
 162     def _real_extract(self, url):
 163         video_id = self._match_id(url)
 164         webpage = self._download_webpage(url, video_id)
 165
 166         # Single video on top of the page
 167         video_link = self._search_regex(
 168             r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
 169             'video page URL', default=None)
 170         if video_link:
 171             video_url = compat_urlparse.urljoin(
 172                 self.http_scheme() + '//spiegel.de/', video_link)
 173             return self.url_result(video_url)
 174
 175         # Multiple embedded videos
 176         embeds = re.findall(
 177             r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
 178             webpage)
 179         entries = [
 180             self.url_result(compat_urlparse.urljoin(
 181                 self.http_scheme() + '//spiegel.de/', embed_path))
 182             for embed_path in embeds]
 183         if embeds:
 184             return self.playlist_result(entries)
 185
 186         return self.playlist_from_matches(
 187             NexxEmbedIE._extract_urls(webpage), ie=NexxEmbedIE.ie_key())