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