[lrt] Extract counters

This commit is contained in:
Sergey M․ 2015-12-27 12:26:48 +06:00
parent f7e1d82d40
commit 15aad84dc5
1 changed files with 12 additions and 0 deletions

View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none,
parse_duration, parse_duration,
remove_end, remove_end,
) )
@ -19,6 +20,8 @@ class LRTIE(InfoExtractor):
'title': 'Septynios Kauno dienos', 'title': 'Septynios Kauno dienos',
'description': 'md5:24d84534c7dc76581e59f5689462411a', 'description': 'md5:24d84534c7dc76581e59f5689462411a',
'duration': 1783, 'duration': 1783,
'view_count': int,
'like_count': int,
}, },
'params': { 'params': {
'skip_download': True, # m3u8 download 'skip_download': True, # m3u8 download
@ -41,6 +44,13 @@ class LRTIE(InfoExtractor):
r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1', r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1',
webpage, 'duration', default=None, group='duration')) webpage, 'duration', default=None, group='duration'))
view_count = int_or_none(self._html_search_regex(
r'<div[^>]+class=(["\']).*?record-desc-seen.*?\1[^>]*>(?P<count>.+?)</div>',
webpage, 'view count', fatal=False, group='count'))
like_count = int_or_none(self._search_regex(
r'<span[^>]+id=(["\'])flikesCount.*?\1>(?P<count>\d+)<',
webpage, 'like count', fatal=False, group='count'))
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
@ -48,4 +58,6 @@ class LRTIE(InfoExtractor):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': description, 'description': description,
'duration': duration, 'duration': duration,
'view_count': view_count,
'like_count': like_count,
} }