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, fatal=True):
  13         error_message = item.find('./errormessage').text
  14         if error_message:
  15             if not fatal:
  16                 return
  17             raise ExtractorError(
  18                 '%s returned error: %s' % (self.IE_NAME, error_message),
  19                 expected=True)
  20
  21         title = item.find('./title').text.strip()
  22         source = item.find('./source').text
  23         extension = item.attrib['type']
  24         thumbnail = item.find('./backimage').text
  25
  26         return {
  27             'title': title,
  28             'url': source,
  29             'ext': extension,
  30             'thumbnail': thumbnail,
  31         }
  32
  33     def _extract_player_xml(self, player_xml_url, id, playlist_title=None):
  34         player_xml = self._download_xml(player_xml_url, id, 'Downloading Player XML')
  35         items = player_xml.findall('./item')
  36
  37         if len(items) == 1:
  38             # one single song
  39             data = self._extract_item(items[0])
  40             data['id'] = id
  41
  42             return data
  43         else:
  44             # playlist of songs
  45             entries = []
  46
  47             for i, item in enumerate(items, 1):
  48                 entry = self._extract_item(item, fatal=False)
  49                 if not entry:
  50                     continue
  51                 entry['id'] = '%s-%d' % (id, i)
  52                 entries.append(entry)
  53
  54             return {
  55                 '_type': 'playlist',
  56                 'id': id,
  57                 'title': playlist_title,
  58                 'entries': entries,
  59             }
  60
  61
  62 class ZingMp3SongIE(ZingMp3BaseInfoExtractor):
  63     _VALID_URL = r'https?://mp3\.zing\.vn/bai-hat/(?P<slug>[^/]+)/(?P<song_id>\w+)\.html'
  64     _TESTS = [{
  65         'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
  66         'md5': 'ead7ae13693b3205cbc89536a077daed',
  67         'info_dict': {
  68             'id': 'ZWZB9WAB',
  69             'title': 'Xa Mãi Xa',
  70             'ext': 'mp3',
  71             'thumbnail': 're:^https?://.*\.jpg$',
  72         },
  73     }]
  74     IE_NAME = 'zingmp3:song'
  75     IE_DESC = 'mp3.zing.vn songs'
  76
  77     def _real_extract(self, url):
  78         matched = re.match(self._VALID_URL, url)
  79         slug = matched.group('slug')
  80         song_id = matched.group('song_id')
  81
  82         webpage = self._download_webpage(
  83             'http://mp3.zing.vn/bai-hat/%s/%s.html' % (slug, song_id), song_id)
  84
  85         player_xml_url = self._search_regex(
  86             r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
  87
  88         return self._extract_player_xml(player_xml_url, song_id)
  89
  90
  91 class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor):
  92     _VALID_URL = r'https?://mp3\.zing\.vn/(?:album|playlist)/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html'
  93     _TESTS = [{
  94         'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
  95         'info_dict': {
  96             '_type': 'playlist',
  97             'id': 'ZWZBWDAF',
  98             'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless',
  99         },
 100         'playlist_count': 10,
 101     }, {
 102         'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
 103         'only_matching': True,
 104     }]
 105     IE_NAME = 'zingmp3:album'
 106     IE_DESC = 'mp3.zing.vn albums'
 107
 108     def _real_extract(self, url):
 109         matched = re.match(self._VALID_URL, url)
 110         slug = matched.group('slug')
 111         album_id = matched.group('album_id')
 112
 113         webpage = self._download_webpage(
 114             'http://mp3.zing.vn/album/%s/%s.html' % (slug, album_id), album_id)
 115         player_xml_url = self._search_regex(
 116             r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
 117
 118         return self._extract_player_xml(
 119             player_xml_url, album_id,
 120             playlist_title=self._og_search_title(webpage))