diff options
author | Sergey M․ <dstftw@gmail.com> | 2016-04-10 23:56:23 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-04-10 23:56:23 +0600 |
commit | 5899e988d55f4c64500721716bb99c5ecf86afc6 (patch) | |
tree | 99c1a58bb6c26fe28b7adc46b6dc9314562d26a5 | |
parent | 4a121d29bb0700beb19e8b6edb5d479e9fe7ac1b (diff) |
[glide] Improve extraction and extract upload info
-rw-r--r-- | youtube_dl/extractor/glide.py | 28 |
1 files changed, 20 insertions, 8 deletions
diff --git a/youtube_dl/extractor/glide.py b/youtube_dl/extractor/glide.py index 0ab23f766..62ff84835 100644 --- a/youtube_dl/extractor/glide.py +++ b/youtube_dl/extractor/glide.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import unified_strdate class GlideIE(InfoExtractor): @@ -15,27 +16,38 @@ class GlideIE(InfoExtractor): 'ext': 'mp4', 'title': 'Damon Timm\'s Glide message', 'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$', + 'uploader': 'Damon Timm', + 'upload_date': '20140919', } } def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( - r'<title>(.*?)</title>', webpage, 'title') + r'<title>(.+?)</title>', webpage, 'title') video_url = self._proto_relative_url(self._search_regex( r'<source[^>]+src=(["\'])(?P<url>.+?)\1', - webpage, 'video URL', group='url'), self.http_scheme()) - thumbnail_url = self._search_regex( - r'<img id="video-thumbnail" src="(.*?)"', - webpage, 'thumbnail url', fatal=False) - thumbnail = ( - thumbnail_url if thumbnail_url is None - else self.http_scheme() + thumbnail_url) + webpage, 'video URL', default=None, + group='url')) or self._og_search_video_url(webpage) + thumbnail = self._proto_relative_url(self._search_regex( + r'<img[^>]+id=["\']video-thumbnail["\'][^>]+src=(["\'])(?P<url>.+?)\1', + webpage, 'thumbnail url', default=None, + group='url')) or self._og_search_thumbnail(webpage) + uploader = self._search_regex( + r'<div[^>]+class=["\']info-name["\'][^>]*>([^<]+)', + webpage, 'uploader', fatal=False) + upload_date = unified_strdate(self._search_regex( + r'<div[^>]+class="info-date"[^>]*>([^<]+)', + webpage, 'upload date', fatal=False)) return { 'id': video_id, 'title': title, 'url': video_url, 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, } |