Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/zdf.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     int_or_none,
   9     unified_strdate,
  10 )
  11
  12
  13 def extract_from_xml_url(ie, video_id, xml_url):
  14     doc = ie._download_xml(
  15         xml_url, video_id,
  16         note='Downloading video info',
  17         errnote='Failed to download video info')
  18
  19     title = doc.find('.//information/title').text
  20     description = doc.find('.//information/detail').text
  21     duration = int(doc.find('.//details/lengthSec').text)
  22     uploader_node = doc.find('.//details/originChannelTitle')
  23     uploader = None if uploader_node is None else uploader_node.text
  24     uploader_id_node = doc.find('.//details/originChannelId')
  25     uploader_id = None if uploader_id_node is None else uploader_id_node.text
  26     upload_date = unified_strdate(doc.find('.//details/airtime').text)
  27
  28     def xml_to_format(fnode):
  29         video_url = fnode.find('url').text
  30         is_available = 'http://www.metafilegenerator' not in video_url
  31
  32         format_id = fnode.attrib['basetype']
  33         format_m = re.match(r'''(?x)
  34             (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
  35             (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
  36         ''', format_id)
  37
  38         ext = format_m.group('container')
  39         proto = format_m.group('proto').lower()
  40
  41         quality = fnode.find('./quality').text
  42         abr = int(fnode.find('./audioBitrate').text) // 1000
  43         vbr_node = fnode.find('./videoBitrate')
  44         vbr = None if vbr_node is None else int(vbr_node.text) // 1000
  45
  46         width_node = fnode.find('./width')
  47         width = None if width_node is None else int_or_none(width_node.text)
  48         height_node = fnode.find('./height')
  49         height = None if height_node is None else int_or_none(height_node.text)
  50
  51         format_note = ''
  52         if not format_note:
  53             format_note = None
  54
  55         return {
  56             'format_id': format_id + '-' + quality,
  57             'url': video_url,
  58             'ext': ext,
  59             'acodec': format_m.group('acodec'),
  60             'vcodec': format_m.group('vcodec'),
  61             'abr': abr,
  62             'vbr': vbr,
  63             'width': width,
  64             'height': height,
  65             'filesize': int_or_none(fnode.find('./filesize').text),
  66             'format_note': format_note,
  67             'protocol': proto,
  68             '_available': is_available,
  69         }
  70
  71     format_nodes = doc.findall('.//formitaeten/formitaet')
  72     formats = list(filter(
  73         lambda f: f['_available'],
  74         map(xml_to_format, format_nodes)))
  75     ie._sort_formats(formats)
  76
  77     return {
  78         'id': video_id,
  79         'title': title,
  80         'description': description,
  81         'duration': duration,
  82         'uploader': uploader,
  83         'uploader_id': uploader_id,
  84         'upload_date': upload_date,
  85         'formats': formats,
  86     }
  87
  88
  89 class ZDFIE(InfoExtractor):
  90     _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
  91
  92     _TEST = {
  93         'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
  94         'info_dict': {
  95             'id': '2037704',
  96             'ext': 'webm',
  97             'title': 'ZDFspezial - Ende des Machtpokers',
  98             'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".',
  99             'duration': 1022,
 100             'uploader': 'spezial',
 101             'uploader_id': '225948',
 102             'upload_date': '20131127',
 103         },
 104         'skip': 'Videos on ZDF.de are depublicised in short order',
 105     }
 106
 107     def _real_extract(self, url):
 108         video_id = self._match_id(url)
 109
 110         xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
 111         return extract_from_xml_url(self, video_id, xml_url)