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