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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     parse_iso8601,
  10 )
  11
  12
  13 class DRBonanzaIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
  15
  16     _TESTS = [{
  17         'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
  18         'md5': 'fe330252ddea607635cf2eb2c99a0af3',
  19         'info_dict': {
  20             'id': '65517',
  21             'ext': 'mp4',
  22             'title': 'Talkshowet - Leonard Cohen',
  23             'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
  24             'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
  25             'timestamp': 1295537932,
  26             'upload_date': '20110120',
  27             'duration': 3664,
  28         },
  29     }, {
  30         'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
  31         'md5': '6dfe039417e76795fb783c52da3de11d',
  32         'info_dict': {
  33             'id': '59410',
  34             'ext': 'mp3',
  35             'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
  36             'description': 'md5:501e5a195749480552e214fbbed16c4e',
  37             'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
  38             'timestamp': 1223274900,
  39             'upload_date': '20081006',
  40             'duration': 7369,
  41         },
  42     }]
  43
  44     def _real_extract(self, url):
  45         url_id = self._match_id(url)
  46         webpage = self._download_webpage(url, url_id)
  47
  48         if url_id:
  49             info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
  50         else:
  51             # Just fetch the first video on that page
  52             info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
  53
  54         asset_id = str(info['AssetId'])
  55         title = info['Title'].rstrip(' \'\"-,.:;!?')
  56         duration = int_or_none(info.get('Duration'), scale=1000)
  57         # First published online. "FirstPublished" contains the date for original airing.
  58         timestamp = parse_iso8601(
  59             re.sub(r'\.\d+$', '', info['Created']))
  60
  61         def parse_filename_info(url):
  62             match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
  63             if match:
  64                 return {
  65                     'width': int(match.group('width')),
  66                     'height': int(match.group('height')),
  67                     'vbr': int(match.group('bitrate')),
  68                     'ext': match.group('ext')
  69                 }
  70             match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
  71             if match:
  72                 return {
  73                     'vbr': int(match.group('bitrate')),
  74                     'ext': match.group(2)
  75                 }
  76             return {}
  77
  78         video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
  79         preferencemap = {
  80             'VideoHigh': -1,
  81             'VideoMid': -2,
  82             'VideoLow': -3,
  83             'Audio': -4,
  84         }
  85
  86         formats = []
  87         for file in info['Files']:
  88             if info['Type'] == "Video":
  89                 if file['Type'] in video_types:
  90                     format = parse_filename_info(file['Location'])
  91                     format.update({
  92                         'url': file['Location'],
  93                         'format_id': file['Type'].replace('Video', ''),
  94                         'preference': preferencemap.get(file['Type'], -10),
  95                     })
  96                     formats.append(format)
  97                 elif file['Type'] == "Thumb":
  98                     thumbnail = file['Location']
  99             elif info['Type'] == "Audio":
 100                 if file['Type'] == "Audio":
 101                     format = parse_filename_info(file['Location'])
 102                     format.update({
 103                         'url': file['Location'],
 104                         'format_id': file['Type'],
 105                         'vcodec': 'none',
 106                     })
 107                     formats.append(format)
 108                 elif file['Type'] == "Thumb":
 109                     thumbnail = file['Location']
 110
 111         description = '%s\n%s\n%s\n' % (
 112             info['Description'], info['Actors'], info['Colophon'])
 113
 114         for f in formats:
 115             f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
 116             f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
 117         self._sort_formats(formats)
 118
 119         display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
 120         display_id = re.sub(r'-+', '-', display_id)
 121
 122         return {
 123             'id': asset_id,
 124             'display_id': display_id,
 125             'title': title,
 126             'formats': formats,
 127             'description': description,
 128             'thumbnail': thumbnail,
 129             'timestamp': timestamp,
 130             'duration': duration,
 131         }