From 7c80519cbf7e3daa029239fbbd147652817877f8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Mon, 20 Jul 2015 21:10:28 +0200 Subject: [PATCH] [youtube] Extract start_time From the 't=*' in the url. Currently youtube-dl doesn't use the value, but it was requested for the mpv plugin. --- youtube_dl/extractor/common.py | 2 ++ youtube_dl/extractor/youtube.py | 14 +++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index b9014fc23..9e8751877 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -183,6 +183,8 @@ class InfoExtractor(object): ["Sports", "Berlin"] is_live: True, False, or None (=unknown). Whether this video is a live stream that goes on instead of a fixed-length video. + start_time: Time in seconds where the reproduction should start, as + specified in the url. Unless mentioned otherwise, the fields should be Unicode strings. diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3d8b31f98..afbd34f4a 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -19,6 +19,7 @@ compat_urllib_parse, compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus, + compat_urllib_parse_urlparse, compat_urllib_request, compat_urlparse, compat_str, @@ -31,6 +32,7 @@ get_element_by_id, int_or_none, orderedSet, + parse_duration, str_to_int, unescapeHTML, unified_strdate, @@ -317,7 +319,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): IE_NAME = 'youtube' _TESTS = [ { - 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', + 'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&t=1s', 'info_dict': { 'id': 'BaW_jenozKc', 'ext': 'mp4', @@ -329,6 +331,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'categories': ['Science & Technology'], 'like_count': int, 'dislike_count': int, + 'start_time': 1, } }, { @@ -889,6 +892,14 @@ def _real_extract(self, url): 'http' if self._downloader.params.get('prefer_insecure', False) else 'https') + start_time = None + parsed_url = compat_urllib_parse_urlparse(url) + for component in [parsed_url.fragment, parsed_url.query]: + query = compat_parse_qs(component) + if 't' in query: + start_time = parse_duration(query['t'][0]) + break + # Extract original video URL from URL with redirection, like age verification, using next_url parameter mobj = re.search(self._NEXT_URL_RE, url) if mobj: @@ -1255,6 +1266,7 @@ def _map_to_format_list(urlmap): 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), 'formats': formats, 'is_live': is_live, + 'start_time': start_time, }