diff options
| author | stepshal <nessento@openmailbox.org> | 2016-09-14 23:03:26 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2016-09-15 23:12:58 +0700 |
| commit | 490b755769a364ca0624390453e36321d5182d3e (patch) | |
| tree | df3d59bf42143069fcee3e3d955cd324d5d9d1f6 | |
| parent | 1dec2c8a0e00e8ed53ddd030347ce9225df9964e (diff) | |
Improve some id regexes
| -rw-r--r-- | youtube_dl/extractor/canvas.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/nfl.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/npo.py | 2 |
3 files changed, 3 insertions, 3 deletions
diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py index ef0691dcd..d183d5d52 100644 --- a/youtube_dl/extractor/canvas.py +++ b/youtube_dl/extractor/canvas.py @@ -71,7 +71,7 @@ class CanvasIE(InfoExtractor): webpage)).strip() video_id = self._html_search_regex( - r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id') + r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', group='id') data = self._download_json( 'https://mediazone.vrt.be/api/v1/%s/assets/%s' diff --git a/youtube_dl/extractor/nfl.py b/youtube_dl/extractor/nfl.py index 200874d68..3930d16f1 100644 --- a/youtube_dl/extractor/nfl.py +++ b/youtube_dl/extractor/nfl.py @@ -165,7 +165,7 @@ class NFLIE(InfoExtractor): group='config')) # For articles, the id in the url is not the video id video_id = self._search_regex( - r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>.+?)\1', + r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', default=video_id, group='id') config = self._download_json(config_url, video_id, 'Downloading player config') url_template = NFLIE.prepend_host( diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 87f5675c7..3293bdb17 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -429,7 +429,7 @@ class SchoolTVIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - r'data-mid=(["\'])(?P<id>.+?)\1', webpage, 'video_id', group='id') + r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id') return { '_type': 'url_transparent', 'ie_key': 'NPO', |