Prepare to upload

[youtubedl] / youtube_dl / extractor / playfm.py

diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py
index 9576aed0e6668189c1959df3166b1e550facc7b0..e766ccca322da0e17389e949cd11fed3a5cb1910 100644 (file)
--- a/youtube_dl/extractor/playfm.py
+++ b/youtube_dl/extractor/playfm.py
@@ -4,85 +4,72 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
-    float_or_none,
     int_or_none,
-    str_to_int,
+    parse_iso8601,
 )
 
 
 class PlayFMIE(InfoExtractor):
     IE_NAME = 'play.fm'
-    _VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?play\.fm/(?P<slug>(?:[^/]+/)+(?P<id>[^/]+))/?(?:$|[?#])'
 
     _TEST = {
-        'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220',
+        'url': 'https://www.play.fm/dan-drastic/sven-tasnadi-leipzig-electronic-music-batofar-paris-fr-2014-07-12',
         'md5': 'c505f8307825a245d0c7ad1850001f22',
         'info_dict': {
-            'id': '137220',
+            'id': '71276',
             'ext': 'mp3',
-            'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
-            'uploader': 'Sven Tasnadi',
-            'uploader_id': 'sventasnadi',
-            'duration': 5627.428,
-            'upload_date': '20140712',
+            'title': 'Sven Tasnadi - LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
+            'description': '',
+            'duration': 5627,
+            'timestamp': 1406033781,
+            'upload_date': '20140722',
+            'uploader': 'Dan Drastic',
+            'uploader_id': '71170',
             'view_count': int,
             'comment_count': int,
-            'thumbnail': 're:^https?://.*\.jpg$',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        upload_date = mobj.group('upload_date')
-
-        rec_data = compat_urllib_parse.urlencode({'rec_id': video_id})
-        req = compat_urllib_request.Request(
-            'http://www.play.fm/flexRead/recording', data=rec_data)
-        req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        rec_doc = self._download_xml(req, video_id)
+        slug = mobj.group('slug')
 
-        error_node = rec_doc.find('./error')
-        if error_node is not None:
-            raise ExtractorError('An error occured: %s (code %s)' % (
-                error_node.text, rec_doc.find('./status').text))
+        recordings = self._download_json(
+            'http://v2api.play.fm/recordings/slug/%s' % slug, video_id)
 
-        recording = rec_doc.find('./recording')
-        title = recording.find('./title').text
-        view_count = str_to_int(recording.find('./stats/playcount').text)
-        comment_count = str_to_int(recording.find('./stats/comments').text)
-        duration = float_or_none(recording.find('./duration').text, scale=1000)
-        thumbnail = recording.find('./image').text
+        error = recordings.get('error')
+        if isinstance(error, dict):
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error.get('message')),
+                expected=True)
 
-        artist = recording.find('./artists/artist')
-        uploader = artist.find('./name').text
-        uploader_id = artist.find('./slug').text
-
-        video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % (
-            'http:', recording.find('./url').text,
-            recording.find('./_class').text, recording.find('./file_id').text,
-            rec_doc.find('./uuid').text, video_id,
-            rec_doc.find('./jingle/file_id').text,
-            'http%3A%2F%2Fwww.play.fm%2Fplayer',
-        )
+        audio_url = recordings['audio']
+        video_id = compat_str(recordings.get('id') or video_id)
+        title = recordings['title']
+        description = recordings.get('description')
+        duration = int_or_none(recordings.get('recordingDuration'))
+        timestamp = parse_iso8601(recordings.get('created_at'))
+        uploader = recordings.get('page', {}).get('title')
+        uploader_id = compat_str(recordings.get('page', {}).get('id'))
+        view_count = int_or_none(recordings.get('playCount'))
+        comment_count = int_or_none(recordings.get('commentCount'))
+        categories = [tag['name'] for tag in recordings.get('tags', []) if tag.get('name')]
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp3',
-            'filesize': int_or_none(recording.find('./size').text),
+            'url': audio_url,
             'title': title,
-            'upload_date': upload_date,
-            'view_count': view_count,
-            'comment_count': comment_count,
+            'description': description,
             'duration': duration,
-            'thumbnail': thumbnail,
+            'timestamp': timestamp,
             'uploader': uploader,
             'uploader_id': uploader_id,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'categories': categories,
         }