diff options
author | Remita Amine <remitamine@gmail.com> | 2016-10-03 15:27:09 +0100 |
---|---|---|
committer | Remita Amine <remitamine@gmail.com> | 2016-10-03 15:27:09 +0100 |
commit | c1084ddb0c87dac450d2b7c1b1cfef386d6f4481 (patch) | |
tree | 9e4c426e515a5b2147c3f15cb514fa6c867ea939 | |
parent | ee5de4e38e3629ffc5d6360e06fa5dcfd43cbeb3 (diff) |
[thisoldhouse] Add new extractor(closes #10837)
-rw-r--r-- | youtube_dl/extractor/extractors.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/thisoldhouse.py | 32 |
2 files changed, 33 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e8928307c..dca4973d4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -892,6 +892,7 @@ from .thesixtyone import TheSixtyOneIE from .thestar import TheStarIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE +from .thisoldhouse import ThisOldHouseIE from .threeqsdn import ThreeQSDNIE from .tinypic import TinyPicIE from .tlc import TlcDeIE diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py new file mode 100644 index 000000000..7629f0d10 --- /dev/null +++ b/youtube_dl/extractor/thisoldhouse.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class ThisOldHouseIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to)/(?P<id>[^/?#]+)' + _TESTS = [{ + 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', + 'md5': '568acf9ca25a639f0c4ff905826b662f', + 'info_dict': { + 'id': '2REGtUDQ', + 'ext': 'mp4', + 'title': 'How to Build a Storage Bench', + 'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.', + 'timestamp': 1442548800, + 'upload_date': '20150918', + } + }, { + 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + drupal_settings = self._parse_json(self._search_regex( + r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', + webpage, 'drupal settings'), display_id) + video_id = drupal_settings['jwplatform']['video_id'] + return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id) |