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