[drtuber] Make dislike count optional (Closes #10297)

This commit is contained in:
Sergey M․ 2016-08-11 23:47:27 +07:00
parent 0c070681c5
commit 0aef0771f8
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -3,7 +3,10 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import str_to_int from ..utils import (
NO_DEFAULT,
str_to_int,
)
class DrTuberIE(InfoExtractor): class DrTuberIE(InfoExtractor):
@ -17,7 +20,6 @@ class DrTuberIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'hot perky blonde naked golf', 'title': 'hot perky blonde naked golf',
'like_count': int, 'like_count': int,
'dislike_count': int,
'comment_count': int, 'comment_count': int,
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'], 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
'thumbnail': 're:https?://.*\.jpg$', 'thumbnail': 're:https?://.*\.jpg$',
@ -43,18 +45,20 @@ def _real_extract(self, url):
r'poster="([^"]+)"', r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', fatal=False)
def extract_count(id_, name): def extract_count(id_, name, default=NO_DEFAULT):
return str_to_int(self._html_search_regex( return str_to_int(self._html_search_regex(
r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_, r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
webpage, '%s count' % name, fatal=False)) webpage, '%s count' % name, default=default, fatal=False))
like_count = extract_count('rate_likes', 'like') like_count = extract_count('rate_likes', 'like')
dislike_count = extract_count('rate_dislikes', 'dislike') dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
comment_count = extract_count('comments_count', 'comment') comment_count = extract_count('comments_count', 'comment')
cats_str = self._search_regex( cats_str = self._search_regex(
r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False) r'<div[^>]+class="categories_list">(.+?)</div>',
categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str) webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(
r'<a title="([^"]+)"', cats_str)
return { return {
'id': video_id, 'id': video_id,