diff options
| author | Roland Hieber <rohieb@rohieb.name> | 2015-07-19 05:09:29 +0200 |
|---|---|---|
| committer | Roland Hieber <rohieb@rohieb.name> | 2015-07-19 05:09:29 +0200 |
| commit | 726adc43ec184b6d7e05cdbc197aa02c53b32347 (patch) | |
| tree | e51019bbe531557c29cbb8f368429c075c3b21d6 /youtube_dl/extractor/tagesschau.py | |
| parent | 3c6ae8b59ed2517891ff19507e4cef2322ef9eb4 (diff) | |
| download | youtube-dl-726adc43ec184b6d7e05cdbc197aa02c53b32347.tar.xz | |
[tagesschau] set description=None for empty descriptions
Diffstat (limited to 'youtube_dl/extractor/tagesschau.py')
| -rw-r--r-- | youtube_dl/extractor/tagesschau.py | 15 |
1 files changed, 6 insertions, 9 deletions
diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py index 682f8df8f..4a755c657 100644 --- a/youtube_dl/extractor/tagesschau.py +++ b/youtube_dl/extractor/tagesschau.py @@ -36,7 +36,7 @@ class TagesschauIE(InfoExtractor): 'info_dict': { 'id': '3771', 'ext': 'mp4', - 'description': '', + 'description': None, 'title': 'Sendung: tagesschau (mit Gebärdensprache) \t14.07.2015 20:00 Uhr', 'thumbnail': 're:^http:.*\.jpg$', } @@ -66,7 +66,7 @@ class TagesschauIE(InfoExtractor): 'info_dict': { 'id': '959', 'ext': 'mp4', - 'description': '', + 'description': None, 'title': 'Sendung: tagesschau vor 20 Jahren \t14.07.2015 22:45 Uhr', 'thumbnail': 're:^http:.*\.jpg$', } @@ -76,7 +76,7 @@ class TagesschauIE(InfoExtractor): 'info_dict': { 'id': '3299', 'ext': 'mp4', - 'description': '', + 'description': None, 'title': 'Nach dem Referendum: Schaltgespräch nach Athen', 'thumbnail': 're:^http:.*\.jpg$', } @@ -154,12 +154,9 @@ class TagesschauIE(InfoExtractor): webpage, 'thumbnail', fatal=False) # there are some videos without description description = "" - try: - description = self._html_search_regex( - r'(?s)<p class="teasertext">(.*?)</p>', - webpage, 'description', fatal=False) - except ExtractorError: - pass + description = self._html_search_regex( + r'(?s)<p class="teasertext">(.*?)</p>', + webpage, 'description', fatal=False, default=None) title = self._html_search_regex( r'<span class="headline".*?>(.*?)</span>', webpage, 'title') |