R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[mytaratata] Improve title & id extraction, add thumbnail

Browse Source
This commit is contained in:
Christophe de Vienne 2018-01-12 13:20:11 +01:00
parent 60098e1491
commit 63c3a458cb
1 changed files with 18 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/mytaratata.py
View File

@ -11,11 +11,11 @@ class MyTaratataIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mytaratata\.com/taratata/(?P<id>[a-zA-Z0-9_\-/]+)' _VALID_URL = r'https?://(?:www\.)?mytaratata\.com/taratata/(?P<id>[a-zA-Z0-9_\-/]+)'
_TEST = { _TEST = {
'url': 'http://mytaratata.com/taratata/519/shaka-ponk-camille-et-julie-berthollet-smells-like-teen-spirit-nirvana', 'url': 'http://mytaratata.com/taratata/519/shaka-ponk-camille-et-julie-berthollet-smells-like-teen-spirit-nirvana',
'md5': 'c2876e18716b350c9de69cfda2662919', 'md5': '99657330eb7dec6d63a329d7f26ec93e',
'info_dict': { 'info_dict': {
'id': '519/shaka-ponk-camille-et-julie-berthollet-smells-like-teen-spirit-nirvana', 'id': '7174',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Taratata - Shaka Ponk / Camille et Julie Berthollet "Smells Like Teen Spirit" (Nirvana)', 'title': u'TARATATA N°519 - Shaka Ponk / Camille et Julie Berthollet "Smells Like Teen Spirit" (Nirvana)',
'uploader': 'Taratata', 'uploader': 'Taratata',
'description': 'Shaka Ponk / Camille et Julie Berthollet "Smells Like Teen Spirit" (Nirvana)', 'description': 'Shaka Ponk / Camille et Julie Berthollet "Smells Like Teen Spirit" (Nirvana)',
# 'thumbnail': r're:^https?://.*\.jpg$', # 'thumbnail': r're:^https?://.*\.jpg$',
@ -31,8 +31,8 @@ class MyTaratataIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ... title = self._og_search_title(webpage)
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title') description = self._og_search_description(webpage)
formats = [] formats = []
@ -43,7 +43,7 @@ class MyTaratataIE(InfoExtractor):
last_vid = None last_vid = None
for url in video_source_re.findall(webpage): for url in video_source_re.findall(webpage):
info_m = re.match(r'.*(?P<vid>[0-9]+)-[a-f0-9]+-(?P<w>[0-9]+)x(?P<h>[0-9]+)\.mp4', url) info_m = re.match(r'.*/(?P<vid>[0-9]+)-[a-f0-9]+-(?P<w>[0-9]+)x(?P<h>[0-9]+)\.mp4', url)
if info_m is None: if info_m is None:
continue continue
vid = info_m.group('vid') vid = info_m.group('vid')
@ -54,15 +54,22 @@ class MyTaratataIE(InfoExtractor):
if vid != last_vid: if vid != last_vid:
break break
formats.append({'url': url, 'width': int(w), 'height': int(h)}) formats.append({
'url': url,
'width': int(w),
'height': int(h),
})
formats = list(sorted(formats, key=lambda f: f['width'])) formats = list(sorted(formats, key=lambda f: f['width']))
return { return {
'id': video_id, 'id': last_vid,
'title': title, 'title': '%s - %s' % (title, description),
'description': self._og_search_description(webpage), 'description': description,
# TODO Improve the filename, id, title.
'uploader': "Taratata", 'uploader': "Taratata",
# TODO more properties (see youtube_dl/extractor/common.py)
'formats': formats, 'formats': formats,
'thumbnails': [
{'url': self._og_search_thumbnail(webpage)},
],
} }