github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-24 18:43:16 +00:00
Code Issues Projects Releases Packages Wiki Activity

[drtuber] Extract counters

Browse source
This commit is contained in:
Sergey M․ 2014-09-02 20:36:26 +07:00
parent 1a94ff6865
commit eade1d7eab
1 changed files with 17 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/drtuber.py
View file

@ -3,6 +3,7 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import str_to_int
class DrTuberIE(InfoExtractor): class DrTuberIE(InfoExtractor):
@ -14,6 +15,9 @@ class DrTuberIE(InfoExtractor):
'id': '1740434', 'id': '1740434',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Hot Perky Blonde Naked Golf', 'title': 'Hot Perky Blonde Naked Golf',
'like_count': int,
'dislike_count': int,
'comment_count': int,
'categories': list, # NSFW 'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$', 'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18, 'age_limit': 18,
@ -36,6 +40,16 @@ def _real_extract(self, url):
r'poster="([^"]+)"', r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', fatal=False)
like_count = str_to_int(self._html_search_regex(
r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._html_search_regex(
r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
webpage, 'like count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'<span class="comments_count">([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
cats_str = self._html_search_regex( cats_str = self._html_search_regex(
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
categories = None if cats_str is None else cats_str.split(' ') categories = None if cats_str is None else cats_str.split(' ')
@ -45,6 +59,9 @@ def _real_extract(self, url):
'url': video_url, 'url': video_url,
'title': title, 'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'categories': categories, 'categories': categories,
'age_limit': self._rta_search(webpage), 'age_limit': self._rta_search(webpage),
} }