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

[FetLife] Add new extractor - handle videos w/o title, set uploader-isotime for title

Browse Source
This commit is contained in:
motophil 2017-01-26 21:16:28 +01:00
parent e4e961df7b
commit 47fc11c99c
1 changed files with 47 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
youtube_dl/extractor/fetlife.py
View File

@ -16,7 +16,8 @@ class FetLifeIE(JWPlatformBaseIE):
_LOGIN_URL = 'https://fetlife.com/users/sign_in' _LOGIN_URL = 'https://fetlife.com/users/sign_in'
_NETRC_MACHINE = 'fetlife' _NETRC_MACHINE = 'fetlife'
_TEST = { _TESTS = [
{
'url': 'https://fetlife.com/users/1537262/videos/660686', 'url': 'https://fetlife.com/users/1537262/videos/660686',
'md5': '83ca9598d9c10afde75a4e730a882560', 'md5': '83ca9598d9c10afde75a4e730a882560',
'info_dict': { 'info_dict': {
@ -35,7 +36,28 @@ class FetLifeIE(JWPlatformBaseIE):
'params': { 'params': {
'usenetrc': True, 'usenetrc': True,
}, },
} },
{
'url': 'https://fetlife.com/users/1972832/videos/672471',
'md5': '4c01a6b57d099f82639f507298424073',
'info_dict': {
'id': '672471',
'thumbnail': r're:^https?://.*\.jpg\?token=[^\s]+$',
'timestamp': 1485368856,
'ext': 'mp4',
'title': 'assman69415-2017-01-25T19:27:36Z',
'uploader': 'assman69415',
'uploader_id': '1972832',
'age_limit': 18,
'upload_date': '20170125',
'duration': 36,
},
'params': {
'usenetrc': True,
},
},
]
def _real_initialize(self): def _real_initialize(self):
"""log into fetlife.com""" """log into fetlife.com"""
@ -72,13 +94,16 @@ class FetLifeIE(JWPlatformBaseIE):
except TypeError: except TypeError:
raise ExtractorError('Unable to extract video data. Not a FetLife Supporter?', expected=True, video_id=video_id) raise ExtractorError('Unable to extract video data. Not a FetLife Supporter?', expected=True, video_id=video_id)
title = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<p[^>]+class=\"description\">([^<]+)', webpage, 'title')
uploader = self._search_regex(r'<div[^>]+class=\"member-info\">[\s\S]+?<a[^>]+class=\"nickname\"[\s\S]+?>([^<]+)', webpage, 'uploader', default=None) uploader = self._search_regex(r'<div[^>]+class=\"member-info\">[\s\S]+?<a[^>]+class=\"nickname\"[\s\S]+?>([^<]+)', webpage, 'uploader', default=None)
uploader_id = self._search_regex(r'<div[^>]+class=\"member-info\">[\s\S]+?<a[^>]+href=\"/users/([0-9]+)', webpage, 'uploader_id', default=None) uploader_id = self._search_regex(r'<div[^>]+class=\"member-info\">[\s\S]+?<a[^>]+href=\"/users/([0-9]+)', webpage, 'uploader_id', default=None)
timeiso = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<time[^>]+datetime\s*=\s*\"([^<]+?)\"', webpage, 'timestamp', default=None)
timestamp = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<time[^>]+>([^<]+)', webpage, 'timestamp', default=None) if timeiso:
if timestamp: titledefault = uploader + '-' + timeiso
timestamp = int(time.mktime(time.strptime(timestamp, "%Y/%m/%d %H:%M:%S +0000"))) timestamp = int(time.mktime(time.strptime(timeiso, "%Y-%m-%dT%H:%M:%SZ")))
else:
titledefault = uploader
timestamp = None
title = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<p[^>]+class=\"description\">([^<]+)', webpage, 'title', default=titledefault)
mobj = re.search(r'clock<[^>]*>\s*(?P<duration_minutes>[0-9]+)m\s*(?P<duration_seconds>[0-9]+)s', webpage) mobj = re.search(r'clock<[^>]*>\s*(?P<duration_minutes>[0-9]+)m\s*(?P<duration_seconds>[0-9]+)s', webpage)
duration_minutes = mobj.groupdict().get('duration_minutes') duration_minutes = mobj.groupdict().get('duration_minutes')