X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fairmozilla.py;h=9e38136b4b795487659145ea81826eccdf4f341d;hb=HEAD;hp=44c20f8861168da0489f4c9cbfc056fcf085aac1;hpb=cd5b4b0bc2876e16656d33156754ce3c05aa1619;p=youtube-dl

diff --git a/youtube_dl/extractor/airmozilla.py b/youtube_dl/extractor/airmozilla.py
index 44c20f886..9e38136b4 100644
--- a/youtube_dl/extractor/airmozilla.py
+++ b/youtube_dl/extractor/airmozilla.py
@@ -4,70 +4,63 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
 
 
 class AirMozillaIE(InfoExtractor):
     _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
     _TEST = {
         'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
-        'md5': '2e3e7486ba5d180e829d453875b9b8bf',
+        'md5': '8d02f53ee39cf006009180e21df1f3ba',
         'info_dict': {
             'id': '6x4q2w',
             'ext': 'mp4',
             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
-            'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
+            'thumbnail': r're:https?://.*/poster\.jpg',
             'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
             'timestamp': 1422487800,
             'upload_date': '20150128',
             'location': 'SFO Commons',
             'duration': 3780,
             'view_count': int,
-            'categories': ['Main'],
+            'categories': ['Main', 'Privacy'],
         }
     }
 
-    _QUALITY_MAP = {
-        '360p': 0,
-        '576p': 1,
-        '640p': 2,
-        '720p': 3,
-    }
-
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
+        video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
 
         embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
-        jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
-        metadata = self._parse_json(jwconfig, video_id)
-
-        formats = []
-        for source in metadata['playlist'][0]['sources']:
-            fmt = {
-                'url': source['file'],
-                'ext': source['type'],
-                'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
-                'resolution': source['label'],
-                'quality': self._QUALITY_MAP.get(source['label'], -1),
-            }
-            formats.append(fmt)
-        self._sort_formats(formats)
+        jwconfig = self._parse_json(self._search_regex(
+            r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
 
-        duration_match = re.search(r'Duration:(?: (?P<H>\d+) hours?)?(?: (?P<M>\d+) minutes?)?', webpage)
+        info_dict = self._parse_jwplayer_data(jwconfig, video_id)
+        view_count = int_or_none(self._html_search_regex(
+            r'Views since archived: ([0-9]+)',
+            webpage, 'view count', fatal=False))
+        timestamp = parse_iso8601(self._html_search_regex(
+            r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
+        duration = parse_duration(self._search_regex(
+            r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
+            webpage, 'duration', fatal=False))
 
-        return {
+        info_dict.update({
             'id': video_id,
             'title': self._og_search_title(webpage),
-            'formats': formats,
             'url': self._og_search_url(webpage),
             'display_id': display_id,
-            'thumbnail': metadata['playlist'][0]['image'],
             'description': self._og_search_description(webpage),
-            'timestamp': parse_iso8601(self._html_search_regex(r'<time datetime="(.*?)"', webpage, 'timestamp')),
+            'timestamp': timestamp,
             'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
-            'duration': int(duration_match.groupdict()['H'] or 0) * 3600 + int(duration_match.groupdict()['M'] or 0) * 60,
-            'view_count': int(self._html_search_regex(r'Views since archived: ([0-9]+)', webpage, 'view count')),
+            'duration': duration,
+            'view_count': view_count,
             'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
-        }
+        })
+
+        return info_dict