diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-11-07 20:02:39 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-11-07 20:02:39 +0600 |
| commit | 6d02b9a392d39c114d3fb58bf7965f62196ccecd (patch) | |
| tree | a19af912d4f731d183650e1682cbc73c723514b3 /youtube_dl/extractor/crunchyroll.py | |
| parent | 2c740cf28d257d2a915195e7cc60f83e6690d2cc (diff) | |
| download | youtube-dl-6d02b9a392d39c114d3fb58bf7965f62196ccecd.zip youtube-dl-6d02b9a392d39c114d3fb58bf7965f62196ccecd.tar.gz youtube-dl-6d02b9a392d39c114d3fb58bf7965f62196ccecd.tar.bz2 | |
[crunchyroll] Fix description extraction
Diffstat (limited to 'youtube_dl/extractor/crunchyroll.py')
| -rw-r--r-- | youtube_dl/extractor/crunchyroll.py | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 9aa5d58..6e5999c 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -21,6 +21,7 @@ from ..utils import ( bytes_to_intlist, intlist_to_bytes, int_or_none, + lowercase_escape, remove_end, unified_strdate, urlencode_postdata, @@ -104,7 +105,7 @@ class CrunchyrollIE(CrunchyrollBaseIE): 'id': '589804', 'ext': 'flv', 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', - 'description': 'md5:fe2743efedb49d279552926d0bd0cd9e', + 'description': 'md5:2fbc01f90b87e8e9137296f37b461c12', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Danny Choo Network', 'upload_date': '20120213', @@ -292,7 +293,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) video_description = self._html_search_regex( - r'"description":"([^"]+)', webpage, 'video_description', default=None) + r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id, + webpage, 'description', default=None) + if video_description: + video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) video_upload_date = self._html_search_regex( [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'], webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) |