_ Git - youtube-dl/blob - youtube_dl/extractor/playfm.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,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     float_or_none,
  14     int_or_none,
  15     str_to_int,
  16 )
  17
  18
  19 class PlayFMIE(InfoExtractor):
  20     IE_NAME = 'play.fm'
  21     _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])'
  22
  23     _TEST = {
  24         'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220',
  25         'md5': 'c505f8307825a245d0c7ad1850001f22',
  26         'info_dict': {
  27             'id': '137220',
  28             'ext': 'mp3',
  29             'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
  30             'uploader': 'Sven Tasnadi',
  31             'uploader_id': 'sventasnadi',
  32             'duration': 5627.428,
  33             'upload_date': '20140712',
  34             'view_count': int,
  35             'comment_count': int,
  36             'thumbnail': 're:^https?://.*\.jpg$',
  37         },
  38     }
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43         upload_date = mobj.group('upload_date')
  44
  45         rec_data = compat_urllib_parse.urlencode({'rec_id': video_id})
  46         req = compat_urllib_request.Request(
  47             'http://www.play.fm/flexRead/recording', data=rec_data)
  48         req.add_header('Content-Type', 'application/x-www-form-urlencoded')
  49         rec_doc = self._download_xml(req, video_id)
  50
  51         error_node = rec_doc.find('./error')
  52         if error_node is not None:
  53             raise ExtractorError('An error occured: %s (code %s)' % (
  54                 error_node.text, rec_doc.find('./status').text))
  55
  56         recording = rec_doc.find('./recording')
  57         title = recording.find('./title').text
  58         view_count = str_to_int(recording.find('./stats/playcount').text)
  59         comment_count = str_to_int(recording.find('./stats/comments').text)
  60         duration = float_or_none(recording.find('./duration').text, scale=1000)
  61         thumbnail = recording.find('./image').text
  62
  63         artist = recording.find('./artists/artist')
  64         uploader = artist.find('./name').text
  65         uploader_id = artist.find('./slug').text
  66
  67         video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % (
  68             'http:', recording.find('./url').text,
  69             recording.find('./_class').text, recording.find('./file_id').text,
  70             rec_doc.find('./uuid').text, video_id,
  71             rec_doc.find('./jingle/file_id').text,
  72             'http%3A%2F%2Fwww.play.fm%2Fplayer',
  73         )
  74
  75         return {
  76             'id': video_id,
  77             'url': video_url,
  78             'ext': 'mp3',
  79             'filesize': int_or_none(recording.find('./size').text),
  80             'title': title,
  81             'upload_date': upload_date,
  82             'view_count': view_count,
  83             'comment_count': comment_count,
  84             'duration': duration,
  85             'thumbnail': thumbnail,
  86             'uploader': uploader,
  87             'uploader_id': uploader_id,
  88         }