Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/zingmp3.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 ExtractorError
   8
   9
  10 class ZingMp3BaseInfoExtractor(InfoExtractor):
  11
  12     def _extract_item(self, item):
  13         error_message = item.find('./errormessage').text
  14         if error_message:
  15             raise ExtractorError(
  16                 '%s returned error: %s' % (self.IE_NAME, error_message),
  17                 expected=True)
  18
  19         title = item.find('./title').text.strip()
  20         source = item.find('./source').text
  21         extension = item.attrib['type']
  22         thumbnail = item.find('./backimage').text
  23
  24         return {
  25             'title': title,
  26             'url': source,
  27             'ext': extension,
  28             'thumbnail': thumbnail,
  29         }
  30
  31     def _extract_player_xml(self, player_xml_url, id, playlist_title=None):
  32         player_xml = self._download_xml(player_xml_url, id, 'Downloading Player XML')
  33         items = player_xml.findall('./item')
  34
  35         if len(items) == 1:
  36             # one single song
  37             data = self._extract_item(items[0])
  38             data['id'] = id
  39
  40             return data
  41         else:
  42             # playlist of songs
  43             entries = []
  44
  45             for i, item in enumerate(items, 1):
  46                 entry = self._extract_item(item)
  47                 entry['id'] = '%s-%d' % (id, i)
  48                 entries.append(entry)
  49
  50             return {
  51                 '_type': 'playlist',
  52                 'id': id,
  53                 'title': playlist_title,
  54                 'entries': entries,
  55             }
  56
  57
  58 class ZingMp3SongIE(ZingMp3BaseInfoExtractor):
  59     _VALID_URL = r'https?://mp3\.zing\.vn/bai-hat/(?P<slug>[^/]+)/(?P<song_id>\w+)\.html'
  60     _TESTS = [{
  61         'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
  62         'md5': 'ead7ae13693b3205cbc89536a077daed',
  63         'info_dict': {
  64             'id': 'ZWZB9WAB',
  65             'title': 'Xa Mãi Xa',
  66             'ext': 'mp3',
  67             'thumbnail': 're:^https?://.*\.jpg$',
  68         },
  69     }]
  70     IE_NAME = 'zingmp3:song'
  71     IE_DESC = 'mp3.zing.vn songs'
  72
  73     def _real_extract(self, url):
  74         matched = re.match(self._VALID_URL, url)
  75         slug = matched.group('slug')
  76         song_id = matched.group('song_id')
  77
  78         webpage = self._download_webpage(
  79             'http://mp3.zing.vn/bai-hat/%s/%s.html' % (slug, song_id), song_id)
  80
  81         player_xml_url = self._search_regex(
  82             r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
  83
  84         return self._extract_player_xml(player_xml_url, song_id)
  85
  86
  87 class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor):
  88     _VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html'
  89     _TESTS = [{
  90         'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
  91         'info_dict': {
  92             '_type': 'playlist',
  93             'id': 'ZWZBWDAF',
  94             'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless',
  95         },
  96         'playlist_count': 10,
  97     }]
  98     IE_NAME = 'zingmp3:album'
  99     IE_DESC = 'mp3.zing.vn albums'
 100
 101     def _real_extract(self, url):
 102         matched = re.match(self._VALID_URL, url)
 103         slug = matched.group('slug')
 104         album_id = matched.group('album_id')
 105
 106         webpage = self._download_webpage(
 107             'http://mp3.zing.vn/album/%s/%s.html' % (slug, album_id), album_id)
 108         player_xml_url = self._search_regex(
 109             r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
 110
 111         return self._extract_player_xml(
 112             player_xml_url, album_id,
 113             playlist_title=self._og_search_title(webpage))