diff options
author | Sergey M. <dstftw@gmail.com> | 2015-07-23 23:33:54 +0600 |
---|---|---|
committer | Sergey M. <dstftw@gmail.com> | 2015-07-23 23:33:54 +0600 |
commit | cdad742700a9a18608a799d86cfe0491e96eaaeb (patch) | |
tree | a9f3a17d34342e3229e93789557f0823e9d0aebe | |
parent | a9e8f60ef686eeeb3d31f2e5211ce176dc8f5298 (diff) | |
parent | 2929fa0e79dfd3a1366e7e23eb4344bc93dd3a10 (diff) |
Merge pull request #6306 from jaimeMF/extract_start_time
[youtube] Extract start_time
-rw-r--r-- | youtube_dl/extractor/common.py | 4 | ||||
-rw-r--r-- | youtube_dl/extractor/youtube.py | 20 |
2 files changed, 23 insertions, 1 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index b9014fc23..1272834c5 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -183,6 +183,10 @@ 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. + end_time: Time in seconds where the reproduction should end, 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 323681960..229fc3a0f 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -19,6 +19,7 @@ from ..compat import ( 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 @@ from ..utils import ( 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&end=9', 'info_dict': { 'id': 'BaW_jenozKc', 'ext': 'mp4', @@ -329,6 +331,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'categories': ['Science & Technology'], 'like_count': int, 'dislike_count': int, + 'start_time': 1, + 'end_time': 9, } }, { @@ -889,6 +893,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'http' if self._downloader.params.get('prefer_insecure', False) else 'https') + start_time = None + end_time = None + parsed_url = compat_urllib_parse_urlparse(url) + for component in [parsed_url.fragment, parsed_url.query]: + query = compat_parse_qs(component) + if start_time is None and 't' in query: + start_time = parse_duration(query['t'][0]) + if start_time is None and 'start' in query: + start_time = parse_duration(query['start'][0]) + if end_time is None and 'end' in query: + end_time = parse_duration(query['end'][0]) + # 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: @@ -1256,6 +1272,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), 'formats': formats, 'is_live': is_live, + 'start_time': start_time, + 'end_time': end_time, } |