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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_parse_qs,
   8     compat_urllib_parse_urlencode,
   9     compat_urllib_parse_urlparse,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     parse_duration,
  15     replace_extension,
  16 )
  17
  18
  19 class FiveMinIE(InfoExtractor):
  20     IE_NAME = '5min'
  21     _VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))'
  22
  23     _TESTS = [
  24         {
  25             # From http://www.engadget.com/2013/11/15/ipad-mini-retina-display-review/
  26             'url': 'http://pshared.5min.com/Scripts/PlayerSeed.js?sid=281&width=560&height=345&playList=518013791',
  27             'md5': '4f7b0b79bf1a470e5004f7112385941d',
  28             'info_dict': {
  29                 'id': '518013791',
  30                 'ext': 'mp4',
  31                 'title': 'iPad Mini with Retina Display Review',
  32                 'duration': 177,
  33             },
  34         },
  35         {
  36             # From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
  37             'url': '5min:518086247',
  38             'md5': 'e539a9dd682c288ef5a498898009f69e',
  39             'info_dict': {
  40                 'id': '518086247',
  41                 'ext': 'mp4',
  42                 'title': 'How to Make a Next-Level Fruit Salad',
  43                 'duration': 184,
  44             },
  45             'skip': 'no longer available',
  46         },
  47     ]
  48     _ERRORS = {
  49         'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
  50         'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
  51         'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
  52         'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
  53         'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
  54         'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
  55     }
  56     _QUALITIES = {
  57         1: {
  58             'width': 640,
  59             'height': 360,
  60         },
  61         2: {
  62             'width': 854,
  63             'height': 480,
  64         },
  65         4: {
  66             'width': 1280,
  67             'height': 720,
  68         },
  69         8: {
  70             'width': 1920,
  71             'height': 1080,
  72         },
  73         16: {
  74             'width': 640,
  75             'height': 360,
  76         },
  77         32: {
  78             'width': 854,
  79             'height': 480,
  80         },
  81         64: {
  82             'width': 1280,
  83             'height': 720,
  84         },
  85         128: {
  86             'width': 640,
  87             'height': 360,
  88         },
  89     }
  90
  91     def _real_extract(self, url):
  92         mobj = re.match(self._VALID_URL, url)
  93         video_id = mobj.group('id')
  94         sid = mobj.group('sid')
  95
  96         if mobj.group('query'):
  97             qs = compat_parse_qs(mobj.group('query'))
  98             if not qs.get('playList'):
  99                 raise ExtractorError('Invalid URL', expected=True)
 100             video_id = qs['playList'][0]
 101             if qs.get('sid'):
 102                 sid = qs['sid'][0]
 103
 104         embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
 105         if not sid:
 106             embed_page = self._download_webpage(embed_url, video_id,
 107                                                 'Downloading embed page')
 108             sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
 109
 110         response = self._download_json(
 111             'https://syn.5min.com/handlers/SenseHandler.ashx?' +
 112             compat_urllib_parse_urlencode({
 113                 'func': 'GetResults',
 114                 'playlist': video_id,
 115                 'sid': sid,
 116                 'isPlayerSeed': 'true',
 117                 'url': embed_url,
 118             }),
 119             video_id)
 120         if not response['success']:
 121             raise ExtractorError(
 122                 '%s said: %s' % (
 123                     self.IE_NAME,
 124                     self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
 125                 expected=True)
 126         info = response['binding'][0]
 127
 128         formats = []
 129         parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
 130             compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
 131         for rendition in info['Renditions']:
 132             if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8':
 133                 continue
 134             else:
 135                 rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
 136                 quality = self._QUALITIES.get(rendition['ID'], {})
 137                 formats.append({
 138                     'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
 139                     'url': rendition_url,
 140                     'width': quality.get('width'),
 141                     'height': quality.get('height'),
 142                 })
 143         self._sort_formats(formats)
 144
 145         return {
 146             'id': video_id,
 147             'title': info['Title'],
 148             'thumbnail': info.get('ThumbURL'),
 149             'duration': parse_duration(info.get('Duration')),
 150             'formats': formats,
 151         }