[adobepass] Add Comcast with fixed _download_webpage calls

[youtube-dl] / youtube_dl / extractor / beatportpro.py

diff --git a/youtube_dl/extractor/beatportpro.py b/youtube_dl/extractor/beatportpro.py
index c3c70fb33a321ff6cbab8a5774bba12a30ceb562..3c7775d3e2762bef7f9424ffa769346dae2d577f 100644 (file)
--- a/youtube_dl/extractor/beatportpro.py
+++ b/youtube_dl/extractor/beatportpro.py
@@ -1,20 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-
 import re
-import json
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
 
 
 class BeatportProIE(InfoExtractor):
-    _VALID_URL = r'https?://pro\.beatport\.com/track/.*/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://pro\.beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371',
         'md5': 'b3c34d8639a2f6a7f734382358478887',
         'info_dict': {
-            'id': 5379371,
-            'display-id': 'synesthesia-original-mix',
+            'id': '5379371',
+            'display_id': 'synesthesia-original-mix',
             'ext': 'mp4',
             'title': 'Froxic - Synesthesia (Original Mix)',
         },
@@ -22,8 +23,8 @@ class BeatportProIE(InfoExtractor):
         'url': 'https://pro.beatport.com/track/love-and-war-original-mix/3756896',
         'md5': 'e44c3025dfa38c6577fbaeb43da43514',
         'info_dict': {
-            'id': 3756896,
-            'display-id': 'love-and-war-original-mix',
+            'id': '3756896',
+            'display_id': 'love-and-war-original-mix',
             'ext': 'mp3',
             'title': 'Wolfgang Gartner - Love & War (Original Mix)',
         },
@@ -31,34 +32,35 @@ class BeatportProIE(InfoExtractor):
         'url': 'https://pro.beatport.com/track/birds-original-mix/4991738',
         'md5': 'a1fd8e8046de3950fd039304c186c05f',
         'info_dict': {
-            'id': 4991738,
-            'display-id': 'birds-original-mix',
+            'id': '4991738',
+            'display_id': 'birds-original-mix',
             'ext': 'mp4',
             'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
         }
     }]
 
     def _real_extract(self, url):
-        track_id = self._match_id(url)
-        webpage = self._download_webpage(url, track_id)
+        mobj = re.match(self._VALID_URL, url)
+        track_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
 
-        # Extract "Playables" JSON information from the page
-        playables = self._search_regex(r'window\.Playables = ({.*?});', webpage,
-                                       'playables info', flags=re.DOTALL)
-        playables = json.loads(playables)
+        playables = self._parse_json(
+            self._search_regex(
+                r'window\.Playables\s*=\s*({.+?});', webpage,
+                'playables info', flags=re.DOTALL),
+            track_id)
 
-        # Find first track with matching ID (always the first one listed?)
         track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
 
-        # Construct title from artist(s), track name, and mix name
         title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
         if track['mix']:
             title += ' (' + track['mix'] + ')'
 
-        # Get format information
         formats = []
         for ext, info in track['preview'].items():
-            if info['url'] is None:
+            if not info['url']:
                 continue
             fmt = {
                 'url': info['url'],
@@ -76,26 +78,26 @@ class BeatportProIE(InfoExtractor):
                 fmt['acodec'] = 'aac'
                 fmt['abr'] = 96
                 fmt['asr'] = 44100
-            formats += [fmt]
-        formats.sort(key=lambda f: f['preference'])
+            formats.append(fmt)
+        self._sort_formats(formats)
 
-        # Get album art as thumbnails
-        imgs = []
+        images = []
         for name, info in track['images'].items():
-            if name == 'dynamic' or info['url'] is None:
+            image_url = info.get('url')
+            if name == 'dynamic' or not image_url:
                 continue
-            img = {
+            image = {
                 'id': name,
-                'url': info['url'],
-                'height': info['height'],
-                'width': info['width'],
+                'url': image_url,
+                'height': int_or_none(info.get('height')),
+                'width': int_or_none(info.get('width')),
             }
-            imgs += [img]
+            images.append(image)
 
         return {
-            'id': track['id'],
-            'display-id': track['slug'],
+            'id': compat_str(track.get('id')) or track_id,
+            'display_id': track.get('slug') or display_id,
             'title': title,
             'formats': formats,
-            'thumbnails': imgs,
+            'thumbnails': images,
         }