Merge branch 'dcn' of github.com:remitamine/youtube-dl into remitamine-dcn

[youtube-dl] / youtube_dl / extractor / lrt.py

diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py
index 42e768ce71fa13bd9fbad77e82da3b18d9d2c751..863efd896b12afa1b674dfb1bcde6d6ffe0214fb 100644 (file)
--- a/youtube_dl/extractor/lrt.py
+++ b/youtube_dl/extractor/lrt.py
@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     parse_duration,
     remove_end,
 )
@@ -19,6 +20,8 @@ class LRTIE(InfoExtractor):
             'title': 'Septynios Kauno dienos',
             'description': 'md5:24d84534c7dc76581e59f5689462411a',
             'duration': 1783,
+            'view_count': int,
+            'like_count': int,
         },
         'params': {
             'skip_download': True,  # m3u8 download
@@ -30,13 +33,23 @@ class LRTIE(InfoExtractor):
         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<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
+            webpage, 'm3u8 url', group='url')
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+
         thumbnail = self._og_search_thumbnail(webpage)
         description = self._og_search_description(webpage)
         duration = parse_duration(self._search_regex(
-            r"var record_len = '([0-9]+:[0-9]+:[0-9]+)';", webpage, 'record_len', fatal=False, default=None))
+            r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1',
+            webpage, 'duration', default=None, group='duration'))
 
-        link = self._search_regex(r'file: "(.*)" \+ location\.hash\.substring\(1\)', webpage, 'link to m3u8')
-        formats = self._extract_m3u8_formats(link, video_id, "mp4")
+        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 {
             'id': video_id,
@@ -45,4 +58,6 @@ class LRTIE(InfoExtractor):
             'thumbnail': thumbnail,
             'description': description,
             'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
         }