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