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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     float_or_none,
   7     int_or_none,
   8     parse_iso8601,
   9     xpath_text,
  10 )
  11
  12
  13 class PhilharmonieDeParisIE(InfoExtractor):
  14     IE_DESC = 'Philharmonie de Paris'
  15     _VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
  16     _TESTS = [{
  17         'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
  18         'info_dict': {
  19             'id': '1032066',
  20             'ext': 'flv',
  21             'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
  22             'timestamp': 1428179400,
  23             'upload_date': '20150404',
  24             'duration': 6592.278,
  25         },
  26         'params': {
  27             # rtmp download
  28             'skip_download': True,
  29         }
  30     }, {
  31         'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
  35         'only_matching': True,
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40
  41         concert = self._download_xml(
  42             'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
  43             video_id).find('./concert')
  44
  45         formats = []
  46         info_dict = {
  47             'id': video_id,
  48             'title': xpath_text(concert, './titre', 'title', fatal=True),
  49             'formats': formats,
  50         }
  51
  52         fichiers = concert.find('./fichiers')
  53         stream = fichiers.attrib['serveurstream']
  54         for fichier in fichiers.findall('./fichier'):
  55             info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
  56             for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
  57                 format_url = fichier.get('url%s' % suffix)
  58                 if not format_url:
  59                     continue
  60                 formats.append({
  61                     'url': stream,
  62                     'play_path': format_url,
  63                     'ext': 'flv',
  64                     'format_id': format_id,
  65                     'width': int_or_none(concert.get('largeur%s' % suffix)),
  66                     'height': int_or_none(concert.get('hauteur%s' % suffix)),
  67                     'quality': quality,
  68                 })
  69         self._sort_formats(formats)
  70
  71         date, hour = concert.get('date'), concert.get('heure')
  72         if date and hour:
  73             info_dict['timestamp'] = parse_iso8601(
  74                 '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
  75         elif date:
  76             info_dict['upload_date'] = date
  77
  78         return info_dict