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

[Iwara] Improve metadata extraction

Browse Source
This commit is contained in:
Alex Aplin 2017-07-30 18:32:01 -04:00
parent 5c9ea67bc0
commit 18414edeb7
1 changed files with 31 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/iwara.py
View File

@ -1,12 +1,18 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse from ..compat import compat_urllib_parse_urlparse
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
mimetype2ext, mimetype2ext,
remove_end, remove_end,
clean_html,
get_element_by_class,
get_elements_by_class,
unified_strdate,
) )
@ -20,6 +26,12 @@ class IwaraIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': '【MMD R-18】ガールフレンド carry_me_off', 'title': '【MMD R-18】ガールフレンド carry_me_off',
'age_limit': 18, 'age_limit': 18,
'upload_date': '20150828',
'uploader': 'Reimu丨Action',
'description': '禁止转载\n\n=acfun=\n=bilibili=\n=youtube=\n\n=stage=\n=motion=\n=camera=\n=dress=',
'comment_count': int,
'like_count': int,
'view_count': int,
}, },
}, { }, {
'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO', 'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
@ -71,6 +83,19 @@ class IwaraIE(InfoExtractor):
title = remove_end(self._html_search_regex( title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara') r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
upload_date = unified_strdate(self._html_search_regex(
r'(\d{4}-\d{2}-\d{2})', webpage, 'upload_date', fatal=False))
uploader = get_element_by_class('username', webpage)
description = clean_html(get_element_by_class('field-type-text-with-summary', webpage).replace('</p>', '<br /></p>'))
comment_count = int_or_none(re.sub('\D', '', get_elements_by_class('title', webpage)[1]))
node_views = clean_html(get_element_by_class('node-views', webpage)).split()
like_count = int_or_none(node_views[0].replace(',', ''))
view_count = int_or_none(node_views[1].replace(',', ''))
formats = [] formats = []
for a_format in video_data: for a_format in video_data:
format_id = a_format.get('resolution') format_id = a_format.get('resolution')
@ -92,4 +117,10 @@ class IwaraIE(InfoExtractor):
'title': title, 'title': title,
'age_limit': age_limit, 'age_limit': age_limit,
'formats': formats, 'formats': formats,
'upload_date': upload_date,
'uploader': uploader,
'description': description,
'comment_count': comment_count,
'like_count': like_count,
'view_count': view_count,
} }