X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c512650955de0b16d37e7fa7fb29ea0985e415bb..d967b1a589a4ead1c13f0c9e17c77cb9a906e556:/youtube_dl/extractor/fourtube.py
diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py
index 7d56b9b..fc4a5a0 100644
--- a/youtube_dl/extractor/fourtube.py
+++ b/youtube_dl/extractor/fourtube.py
@@ -4,11 +4,10 @@ import re
from .common import InfoExtractor
from ..utils import (
- compat_urllib_request,
- unified_strdate,
- str_to_int,
parse_duration,
- clean_html,
+ parse_iso8601,
+ sanitized_Request,
+ str_to_int,
)
@@ -26,70 +25,93 @@ class FourTubeIE(InfoExtractor):
'uploader': 'WCP Club',
'uploader_id': 'wcp-club',
'upload_date': '20131031',
+ 'timestamp': 1383263892,
'duration': 583,
+ 'view_count': int,
+ 'like_count': int,
+ 'categories': list,
+ 'age_limit': 18,
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
- webpage_url = 'http://www.4tube.com/videos/' + video_id
- webpage = self._download_webpage(webpage_url, video_id)
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
- self.report_extraction(video_id)
+ title = self._html_search_meta('name', webpage)
+ timestamp = parse_iso8601(self._html_search_meta(
+ 'uploadDate', webpage))
+ thumbnail = self._html_search_meta('thumbnailUrl', webpage)
+ uploader_id = self._html_search_regex(
+ r'',
+ webpage, 'uploader id', fatal=False)
+ uploader = self._html_search_regex(
+ r'',
+ webpage, 'uploader', fatal=False)
- playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
- media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
- sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
- title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
- thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+ categories_html = self._search_regex(
+ r'(?s)>\s*Categories / Tags\s*.*?',
+ webpage, 'categories', fatal=False)
+ categories = None
+ if categories_html:
+ categories = [
+ c.strip() for c in re.findall(
+ r'(?s)(.*?)', categories_html)]
- uploader_str = self._search_regex(r'Uploaded by(.*?)', webpage, 'uploader', fatal=False)
- mobj = re.search(r'(?P[^<]+)', uploader_str)
- (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+ view_count = str_to_int(self._search_regex(
+ r'',
+ webpage, 'view count', fatal=False))
+ like_count = str_to_int(self._search_regex(
+ r'',
+ webpage, 'like count', fatal=False))
+ duration = parse_duration(self._html_search_meta('duration', webpage))
- upload_date = None
- view_count = None
- duration = None
- description = self._html_search_meta('description', webpage, 'description')
- if description:
- upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
- fatal=False)
- if upload_date:
- upload_date = unified_strdate(upload_date)
- view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
- if view_count:
- view_count = str_to_int(view_count)
- duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
+ media_id = self._search_regex(
+ r'