_ Git - youtube-dl/blob - youtube_dl/extractor/wrzuta.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     qualities,
  10     remove_start,
  11 )
  12
  13
  14 class WrzutaIE(InfoExtractor):
  15     IE_NAME = 'wrzuta.pl'
  16
  17     _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/(?P<typ>film|audio)/(?P<id>[0-9a-zA-Z]+)'
  18
  19     _TESTS = [{
  20         'url': 'http://laboratoriumdextera.wrzuta.pl/film/aq4hIZWrkBu/nike_football_the_last_game',
  21         'md5': '9e67e05bed7c03b82488d87233a9efe7',
  22         'info_dict': {
  23             'id': 'aq4hIZWrkBu',
  24             'ext': 'mp4',
  25             'title': 'Nike Football: The Last Game',
  26             'duration': 307,
  27             'uploader_id': 'laboratoriumdextera',
  28             'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
  29         },
  30     }, {
  31         'url': 'http://jolka85.wrzuta.pl/audio/063jOPX5ue2/liber_natalia_szroeder_-_teraz_ty',
  32         'md5': 'bc78077859bea7bcfe4295d7d7fc9025',
  33         'info_dict': {
  34             'id': '063jOPX5ue2',
  35             'ext': 'ogg',
  36             'title': 'Liber & Natalia Szroeder - Teraz Ty',
  37             'duration': 203,
  38             'uploader_id': 'jolka85',
  39             'description': 'md5:2d2b6340f9188c8c4cd891580e481096',
  40         },
  41     }]
  42
  43     def _real_extract(self, url):
  44         mobj = re.match(self._VALID_URL, url)
  45         video_id = mobj.group('id')
  46         typ = mobj.group('typ')
  47         uploader = mobj.group('uploader')
  48
  49         webpage = self._download_webpage(url, video_id)
  50
  51         quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
  52
  53         audio_table = {'flv': 'mp3', 'webm': 'ogg', '???': 'mp3'}
  54
  55         embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id)
  56
  57         formats = []
  58         for media in embedpage['url']:
  59             fmt = media['type'].split('@')[0]
  60             if typ == 'audio':
  61                 ext = audio_table.get(fmt, fmt)
  62             else:
  63                 ext = fmt
  64
  65             formats.append({
  66                 'format_id': '%s_%s' % (ext, media['quality'].lower()),
  67                 'url': media['url'],
  68                 'ext': ext,
  69                 'quality': quality(media['quality']),
  70             })
  71
  72         self._sort_formats(formats)
  73
  74         return {
  75             'id': video_id,
  76             'title': self._og_search_title(webpage),
  77             'thumbnail': self._og_search_thumbnail(webpage),
  78             'formats': formats,
  79             'duration': int_or_none(embedpage['duration']),
  80             'uploader_id': uploader,
  81             'description': self._og_search_description(webpage),
  82             'age_limit': embedpage.get('minimalAge', 0),
  83         }
  84
  85
  86 class WrzutaPlaylistIE(InfoExtractor):
  87     """
  88         this class covers extraction of wrzuta playlist entries
  89         the extraction process bases on following steps:
  90         * collect information of playlist size
  91         * download all entries provided on
  92           the playlist webpage (the playlist is split
  93           on two pages: first directly reached from webpage
  94           second: downloaded on demand by ajax call and rendered
  95           using the ajax call response)
  96         * in case size of extracted entries not reached total number of entries
  97           use the ajax call to collect the remaining entries
  98     """
  99
 100     IE_NAME = 'wrzuta.pl:playlist'
 101     _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/playlista/(?P<id>[0-9a-zA-Z]+)'
 102     _TESTS = [{
 103         'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR/moja_muza',
 104         'playlist_mincount': 14,
 105         'info_dict': {
 106             'id': '7XfO4vE84iR',
 107             'title': 'Moja muza',
 108         },
 109     }, {
 110         'url': 'http://heroesf70.wrzuta.pl/playlista/6Nj3wQHx756/lipiec_-_lato_2015_muzyka_swiata',
 111         'playlist_mincount': 144,
 112         'info_dict': {
 113             'id': '6Nj3wQHx756',
 114             'title': 'Lipiec - Lato 2015 Muzyka Świata',
 115         },
 116     }, {
 117         'url': 'http://miromak71.wrzuta.pl/playlista/7XfO4vE84iR',
 118         'only_matching': True,
 119     }]
 120
 121     def _real_extract(self, url):
 122         mobj = re.match(self._VALID_URL, url)
 123         playlist_id = mobj.group('id')
 124         uploader = mobj.group('uploader')
 125
 126         webpage = self._download_webpage(url, playlist_id)
 127
 128         playlist_size = int_or_none(self._html_search_regex(
 129             (r'<div[^>]+class=["\']playlist-counter["\'][^>]*>\d+/(\d+)',
 130              r'<div[^>]+class=["\']all-counter["\'][^>]*>(.+?)</div>'),
 131             webpage, 'playlist size', default=None))
 132
 133         playlist_title = remove_start(
 134             self._og_search_title(webpage), 'Playlista: ')
 135
 136         entries = []
 137         if playlist_size:
 138             entries = [
 139                 self.url_result(entry_url)
 140                 for _, entry_url in re.findall(
 141                     r'<a[^>]+href=(["\'])(http.+?)\1[^>]+class=["\']playlist-file-page',
 142                     webpage)]
 143             if playlist_size > len(entries):
 144                 playlist_content = self._download_json(
 145                     'http://%s.wrzuta.pl/xhr/get_playlist_offset/%s' % (uploader, playlist_id),
 146                     playlist_id,
 147                     'Downloading playlist JSON',
 148                     'Unable to download playlist JSON')
 149                 entries.extend([
 150                     self.url_result(entry['filelink'])
 151                     for entry in playlist_content.get('files', []) if entry.get('filelink')])
 152
 153         return self.playlist_result(entries, playlist_id, playlist_title)