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

[pornhd] added like count to info dict

Browse Source
This commit is contained in:
jonathanjones6fe 2019-02-03 13:39:44 -04:00
parent 4c125b8181
commit 041bad8508
2 changed files with 14 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
youtube_dl/extractor/pornhd.py
View File

@ -85,6 +85,9 @@ class PornHdIE(InfoExtractor):
r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage, r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
'thumbnail', fatal=False, group='url') 'thumbnail', fatal=False, group='url')
like_count = int_or_none(self._search_regex(
r'class="save-count">(\d+)<', webpage, 'like_count', fatal=False))
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
@ -94,4 +97,5 @@ class PornHdIE(InfoExtractor):
'view_count': view_count, 'view_count': view_count,
'formats': formats, 'formats': formats,
'age_limit': 18, 'age_limit': 18,
'like_count': like_count,
} }

22
youtube_dl/extractor/pornhub.py
View File

@ -16,6 +16,7 @@ from .openload import PhantomJSwrapper
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
js_to_json,
orderedSet, orderedSet,
remove_quotes, remove_quotes,
str_to_int, str_to_int,
@ -302,17 +303,14 @@ class PornHubIE(PornHubBaseIE):
comment_count = self._extract_count( comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
def _get_items(class_name): page_params = self._parse_json(self._search_regex(
div = self._search_regex( r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
r'<div class="' + class_name + '">([\S\s]+?)</div>', webpage, 'page parameters', group='data', default='{}'),
webpage, class_name, default=None) video_id, transform_source=js_to_json, fatal=False)
if div: tags = categories = None
return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)] if page_params:
else: tags = page_params.get('tags', '').split(',')
return None categories = page_params.get('categories', '').split(',')
categories = _get_items('categoriesWrapper')
tags = _get_items('tagsWrapper')
return { return {
'id': video_id, 'id': video_id,
@ -448,4 +446,4 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
break break
entries.extend(page_entries) entries.extend(page_entries)
return self.playlist_result(entries, user_id) return self.playlist_result(entries, user_id)