X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Flrt.py;h=1072405b30c7663d19ddc4df86f858d94952fda5;hb=fd8c8c7dcdb722ae0ed96b8ceb4c844c87f2c896;hp=db5df40789c5167e1062364a860fa9bc1d369218;hpb=9a76f416ce67eaaf9c1cdd9058a4e509950950ef;p=youtube-dl diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py index db5df4078..1072405b3 100644 --- a/youtube_dl/extractor/lrt.py +++ b/youtube_dl/extractor/lrt.py @@ -1,13 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor from ..utils import ( - determine_ext, - js_to_json, + int_or_none, parse_duration, remove_end, ) @@ -24,40 +20,37 @@ class LRTIE(InfoExtractor): 'title': 'Septynios Kauno dienos', 'description': 'md5:24d84534c7dc76581e59f5689462411a', 'duration': 1783, + 'view_count': int, + 'like_count': int, }, 'params': { - 'skip_download': True, # HLS download + 'skip_download': True, # m3u8 download }, - } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = remove_end(self._og_search_title(webpage), ' - LRT') + m3u8_url = self._search_regex( + r'file\s*:\s*(["\'])(?P.+?)\1\s*\+\s*location\.hash\.substring\(1\)', + webpage, 'm3u8 url', group='url') + formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') + self._sort_formats(formats) + thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage) duration = parse_duration(self._search_regex( - r"'duration':\s*'([^']+)',", webpage, - 'duration', fatal=False, default=None)) + r'var\s+record_len\s*=\s*(["\'])(?P[0-9]+:[0-9]+:[0-9]+)\1', + webpage, 'duration', default=None, group='duration')) - formats = [] - for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage): - data = json.loads(js_to_json(js)) - if data['provider'] == 'rtmp': - formats.append({ - 'format_id': 'rtmp', - 'ext': determine_ext(data['file']), - 'url': data['streamer'], - 'play_path': 'mp4:%s' % data['file'], - 'preference': -1, - }) - else: - formats.extend( - self._extract_m3u8_formats(data['file'], video_id, 'mp4')) + view_count = int_or_none(self._html_search_regex( + r']+class=(["\']).*?record-desc-seen.*?\1[^>]*>(?P.+?)', + webpage, 'view count', fatal=False, group='count')) + like_count = int_or_none(self._search_regex( + r']+id=(["\'])flikesCount.*?\1>(?P\d+)<', + webpage, 'like count', fatal=False, group='count')) return { 'id': video_id, @@ -66,4 +59,6 @@ class LRTIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, }