aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-02-09 21:30:48 +0600
committerSergey M․ <dstftw@gmail.com>2016-02-09 21:30:48 +0600
commitb081350bd943d7595acda70240d2aaa749fc34b3 (patch)
treeca3354049052563000319d329e8bc34e057ac364
parent16f1430ba6fc1dc3fe0baf587f4461f37b62466a (diff)
[mailru] Improve and modernize
-rw-r--r--youtube_dl/extractor/mailru.py53
1 files changed, 32 insertions, 21 deletions
diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py
index 09424620b..b7671f16e 100644
--- a/youtube_dl/extractor/mailru.py
+++ b/youtube_dl/extractor/mailru.py
@@ -4,6 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ remove_end,
+)
class MailRuIE(InfoExtractor):
@@ -86,29 +90,36 @@ class MailRuIE(InfoExtractor):
'http://api.video.mail.ru/videos/%s.json?new=1' % video_id,
video_id, 'Downloading video JSON')
- author = video_data['author']
- uploader = author['name']
- uploader_id = author.get('id') or author.get('email')
- view_count = video_data.get('views_count')
+ formats = []
+ for f in video_data['videos']:
+ video_url = f.get('url')
+ if not video_url:
+ continue
+ format_id = f.get('key')
+ height = int_or_none(self._search_regex(
+ r'^(\d+)[pP]$', format_id, 'height', default=None)) if format_id else None
+ formats.append({
+ 'url': video_url,
+ 'format_id': format_id,
+ 'height': height,
+ })
+ self._sort_formats(formats)
meta_data = video_data['meta']
- content_id = '%s_%s' % (
- meta_data.get('accId', ''), meta_data['itemId'])
- title = meta_data['title']
- if title.endswith('.mp4'):
- title = title[:-4]
- thumbnail = meta_data['poster']
- duration = meta_data['duration']
- timestamp = meta_data['timestamp']
-
- formats = [
- {
- 'url': video['url'],
- 'format_id': video['key'],
- 'height': int(video['key'].rstrip('p'))
- } for video in video_data['videos']
- ]
- self._sort_formats(formats)
+ title = remove_end(meta_data['title'], '.mp4')
+
+ author = video_data.get('author')
+ uploader = author.get('name')
+ uploader_id = author.get('id') or author.get('email')
+ view_count = int_or_none(video_data.get('viewsCount') or video_data.get('views_count'))
+
+ acc_id = meta_data.get('accId')
+ item_id = meta_data.get('itemId')
+ content_id = '%s_%s' % (acc_id, item_id) if acc_id and item_id else video_id
+
+ thumbnail = meta_data.get('poster')
+ duration = int_or_none(meta_data.get('duration'))
+ timestamp = int_or_none(meta_data.get('timestamp'))
return {
'id': content_id,