diff options
author | Sergey M․ <dstftw@gmail.com> | 2016-11-04 21:32:30 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-11-04 21:32:30 +0700 |
commit | f3c705f8ec3505240bdfbe622693c3cd2ce10857 (patch) | |
tree | 43f6dc37f507d6a1d069d69cfd48683fb3dab587 /youtube_dl/extractor | |
parent | f93ac1d17571d6ddf9cfb56f0bb51bdef6a04799 (diff) |
[fox9] Add extractor (closes #11110)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/fox9.py | 43 |
2 files changed, 44 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 499239a22..d7ad5b8fc 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -296,6 +296,7 @@ from .footyroom import FootyRoomIE from .formula1 import Formula1IE from .fourtube import FourTubeIE from .fox import FOXIE +from .fox9 import FOX9IE from .foxgay import FoxgayIE from .foxnews import ( FoxNewsIE, diff --git a/youtube_dl/extractor/fox9.py b/youtube_dl/extractor/fox9.py new file mode 100644 index 000000000..56d9975d0 --- /dev/null +++ b/youtube_dl/extractor/fox9.py @@ -0,0 +1,43 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .anvato import AnvatoIE +from ..utils import js_to_json + + +class FOX9IE(AnvatoIE): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story' + _TESTS = [{ + 'url': 'http://www.fox9.com/news/215123287-story', + 'md5': 'd6e1b2572c3bab8a849c9103615dd243', + 'info_dict': { + 'id': '314473', + 'ext': 'mp4', + 'title': 'Bear climbs tree in downtown Duluth', + 'description': 'md5:6a36bfb5073a411758a752455408ac90', + 'duration': 51, + 'timestamp': 1478123580, + 'upload_date': '20161102', + 'uploader': 'EPFOX', + 'categories': ['News', 'Sports'], + 'tags': ['news', 'video'], + }, + }, { + 'url': 'http://www.fox9.com/news/investigators/214070684-story', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._parse_json( + self._search_regex( + r'AnvatoPlaylist\s*\(\s*(\[.+?\])\s*\)\s*;', + webpage, 'anvato playlist'), + video_id, transform_source=js_to_json)[0]['video'] + + return self._get_anvato_videos( + 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b', + video_id) |