youtube_dl/extractor/yam.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 compat_urlparse
   8 from ..utils import (
   9     float_or_none,
  10     month_by_abbreviation,
  11     ExtractorError,
  12 )
  13
  14
  15 class YamIE(InfoExtractor):
  16     _VALID_URL = r'http://mymedia.yam.com/m/(?P<id>\d+)'
  17
  18     _TESTS = [{
  19         # An audio hosted on Yam
  20         'url': 'http://mymedia.yam.com/m/2283921',
  21         'md5': 'c011b8e262a52d5473d9c2e3c9963b9c',
  22         'info_dict': {
  23             'id': '2283921',
  24             'ext': 'mp3',
  25             'title': '發現 - 趙薇 京華煙雲主題曲',
  26             'uploader_id': 'princekt',
  27             'upload_date': '20080807',
  28             'duration': 313.0,
  29         }
  30     }, {
  31         # An external video hosted on YouTube
  32         'url': 'http://mymedia.yam.com/m/3599430',
  33         'md5': '03127cf10d8f35d120a9e8e52e3b17c6',
  34         'info_dict': {
  35             'id': 'CNpEoQlrIgA',
  36             'ext': 'mp4',
  37             'upload_date': '20150306',
  38             'uploader': '新莊社大瑜伽社',
  39             'description': 'md5:11e2e405311633ace874f2e6226c8b17',
  40             'uploader_id': '2323agoy',
  41             'title': '20090412陽明山二子坪-1',
  42         },
  43         'skip': 'Video does not exist',
  44     }, {
  45         'url': 'http://mymedia.yam.com/m/3598173',
  46         'info_dict': {
  47             'id': '3598173',
  48             'ext': 'mp4',
  49         },
  50         'skip': 'cause Yam system error',
  51     }, {
  52         'url': 'http://mymedia.yam.com/m/3599437',
  53         'info_dict': {
  54             'id': '3599437',
  55             'ext': 'mp4',
  56         },
  57         'skip': 'invalid YouTube URL',
  58     }]
  59
  60     def _real_extract(self, url):
  61         video_id = self._match_id(url)
  62         page = self._download_webpage(url, video_id)
  63
  64         # Check for errors
  65         system_msg = self._html_search_regex(
  66             r'系統訊息(?:<br>|\n|\r)*([^<>]+)<br>', page, 'system message',
  67             default=None)
  68         if system_msg:
  69             raise ExtractorError(system_msg, expected=True)
  70
  71         # Is it hosted externally on YouTube?
  72         youtube_url = self._html_search_regex(
  73             r'<embed src="(http://www.youtube.com/[^"]+)"',
  74             page, 'YouTube url', default=None)
  75         if youtube_url:
  76             return self.url_result(youtube_url, 'Youtube')
  77
  78         api_page = self._download_webpage(
  79             'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id,
  80             note='Downloading API page')
  81         api_result_obj = compat_urlparse.parse_qs(api_page)
  82
  83         uploader_id = self._html_search_regex(
  84             r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z]+)"',
  85             page, 'uploader id', fatal=False)
  86         mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2})  ' +
  87                          r'(?P<day>\d{1,2}), (?P<year>\d{4})', page)
  88         if mobj:
  89             upload_date = '%s%02d%02d' % (
  90                 mobj.group('year'),
  91                 month_by_abbreviation(mobj.group('mon')),
  92                 int(mobj.group('day')))
  93         else:
  94             upload_date = None
  95         duration = float_or_none(api_result_obj['totaltime'][0], scale=1000)
  96
  97         return {
  98             'id': video_id,
  99             'url': api_result_obj['mp3file'][0],
 100             'title': self._html_search_meta('description', page),
 101             'duration': duration,
 102             'uploader_id': uploader_id,
 103             'upload_date': upload_date,
 104         }