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

[FetLife] add new extractor - also extract duration and like_count

Browse Source
This commit is contained in:
motophil 2017-01-23 23:38:36 +01:00
parent 8bcaa14ce8
commit e4e961df7b
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
youtube_dl/extractor/fetlife.py
View File

@ -1,6 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import time import time
import re
from .jwplatform import JWPlatformBaseIE from .jwplatform import JWPlatformBaseIE
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
@ -28,6 +29,8 @@ class FetLifeIE(JWPlatformBaseIE):
'uploader_id': '1537262', 'uploader_id': '1537262',
'age_limit': 18, 'age_limit': 18,
'upload_date': '20170110', 'upload_date': '20170110',
'duration': 91,
}, },
'params': { 'params': {
'usenetrc': True, 'usenetrc': True,
@ -72,10 +75,21 @@ class FetLifeIE(JWPlatformBaseIE):
title = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<p[^>]+class=\"description\">([^<]+)', webpage, 'title') 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)
timestamp = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<time[^>]+>([^<]+)', webpage, 'timestamp', default=None) timestamp = self._search_regex(r'<section[^>]+id=\"video_caption\">[\s\S]+?<time[^>]+>([^<]+)', webpage, 'timestamp', default=None)
if timestamp: if timestamp:
timestamp = int(time.mktime(time.strptime(timestamp, "%Y/%m/%d %H:%M:%S +0000"))) timestamp = int(time.mktime(time.strptime(timestamp, "%Y/%m/%d %H:%M:%S +0000")))
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_seconds = mobj.groupdict().get('duration_seconds')
if (duration_minutes is not None) and (duration_seconds is not None):
duration = int(duration_minutes) * 60 + int(duration_seconds)
like_count = self._search_regex(r'[0-9]+\s*Love\s*it', webpage, 'like_count', default=None)
if like_count:
like_count = int(like_count)
video_data.update({ video_data.update({
'id': video_id, 'id': video_id,
'title': title, 'title': title,
@ -83,6 +97,8 @@ class FetLifeIE(JWPlatformBaseIE):
'timestamp': timestamp, 'timestamp': timestamp,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'age_limit': 18, 'age_limit': 18,
'duration': duration,
'like_count': like_count,
}) })
return video_data return video_data