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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse_urlparse,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14     update_url_query,
  15     xpath_element,
  16     xpath_text,
  17 )
  18
  19
  20 class AfreecaTVIE(InfoExtractor):
  21     IE_DESC = 'afreecatv.com'
  22     _VALID_URL = r'''(?x)
  23                     https?://
  24                         (?:
  25                             (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
  26                             (?:
  27                                 /app/(?:index|read_ucc_bbs)\.cgi|
  28                                 /player/[Pp]layer\.(?:swf|html)
  29                             )\?.*?\bnTitleNo=|
  30                             vod\.afreecatv\.com/PLAYER/STATION/
  31                         )
  32                         (?P<id>\d+)
  33                     '''
  34     _TESTS = [{
  35         'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
  36         'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
  37         'info_dict': {
  38             'id': '36164052',
  39             'ext': 'mp4',
  40             'title': '데일리 에이프릴 요정들의 시상식!',
  41             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  42             'uploader': 'dailyapril',
  43             'uploader_id': 'dailyapril',
  44             'upload_date': '20160503',
  45         }
  46     }, {
  47         'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
  48         'info_dict': {
  49             'id': '36153164',
  50             'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  51             'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
  52             'uploader': 'dailyapril',
  53             'uploader_id': 'dailyapril',
  54         },
  55         'playlist_count': 2,
  56         'playlist': [{
  57             'md5': 'd8b7c174568da61d774ef0203159bf97',
  58             'info_dict': {
  59                 'id': '36153164_1',
  60                 'ext': 'mp4',
  61                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  62                 'upload_date': '20160502',
  63             },
  64         }, {
  65             'md5': '58f2ce7f6044e34439ab2d50612ab02b',
  66             'info_dict': {
  67                 'id': '36153164_2',
  68                 'ext': 'mp4',
  69                 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
  70                 'upload_date': '20160502',
  71             },
  72         }],
  73     }, {
  74         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
  75         'only_matching': True,
  76     }, {
  77         'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
  78         'only_matching': True,
  79     }]
  80
  81     @staticmethod
  82     def parse_video_key(key):
  83         video_key = {}
  84         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
  85         if m:
  86             video_key['upload_date'] = m.group('upload_date')
  87             video_key['part'] = m.group('part')
  88         return video_key
  89
  90     def _real_extract(self, url):
  91         video_id = self._match_id(url)
  92         parsed_url = compat_urllib_parse_urlparse(url)
  93         info_url = compat_urlparse.urlunparse(parsed_url._replace(
  94             netloc='afbbs.afreecatv.com:8080',
  95             path='/api/video/get_video_info.php'))
  96
  97         video_xml = self._download_xml(
  98             update_url_query(info_url, {'nTitleNo': video_id}), video_id)
  99
 100         if xpath_element(video_xml, './track/video/file') is None:
 101             raise ExtractorError('Specified AfreecaTV video does not exist',
 102                                  expected=True)
 103
 104         title = xpath_text(video_xml, './track/title', 'title')
 105         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
 106         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
 107         duration = int_or_none(xpath_text(video_xml, './track/duration',
 108                                           'duration'))
 109         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
 110
 111         entries = []
 112         for i, video_file in enumerate(video_xml.findall('./track/video/file')):
 113             video_key = self.parse_video_key(video_file.get('key', ''))
 114             if not video_key:
 115                 continue
 116             entries.append({
 117                 'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
 118                 'title': title,
 119                 'upload_date': video_key.get('upload_date'),
 120                 'duration': int_or_none(video_file.get('duration')),
 121                 'url': video_file.text,
 122             })
 123
 124         info = {
 125             'id': video_id,
 126             'title': title,
 127             'uploader': uploader,
 128             'uploader_id': uploader_id,
 129             'duration': duration,
 130             'thumbnail': thumbnail,
 131         }
 132
 133         if len(entries) > 1:
 134             info['_type'] = 'multi_video'
 135             info['entries'] = entries
 136         elif len(entries) == 1:
 137             info['url'] = entries[0]['url']
 138             info['upload_date'] = entries[0].get('upload_date')
 139         else:
 140             raise ExtractorError(
 141                 'No files found for the specified AfreecaTV video, either'
 142                 ' the URL is incorrect or the video has been made private.',
 143                 expected=True)
 144
 145         return info