aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorremitamine <remitamine@gmail.com>2015-12-19 18:26:28 +0100
committerremitamine <remitamine@gmail.com>2015-12-19 18:26:28 +0100
commite0f06eae432e592b159237f2ce9813449431cc7b (patch)
tree9b2028399900d7f1da3cefc1974809fe9b939b1e
parent0f206ee81447349f9ec8c430de4868a86020564c (diff)
[fktv] fix info extraction
-rw-r--r--youtube_dl/extractor/fktv.py34
1 files changed, 15 insertions, 19 deletions
diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py
index 40ea27895..5f6e65dae 100644
--- a/youtube_dl/extractor/fktv.py
+++ b/youtube_dl/extractor/fktv.py
@@ -1,12 +1,10 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
- ExtractorError,
+ js_to_json,
)
@@ -32,24 +30,22 @@ class FKTVIE(InfoExtractor):
'http://fernsehkritik.tv/folge-%s/play' % episode, episode)
title = clean_html(self._html_search_regex(
'<h3>([^<]+)</h3>', webpage, 'title'))
- matches = re.search(
- r'(?s)<video(?:(?!poster)[^>])+(?:poster="([^"]+)")?[^>]*>(.*)</video>',
- webpage)
- if matches is None:
- raise ExtractorError('Unable to extract the video')
-
- poster, sources = matches.groups()
- if poster is None:
- self.report_warning('unable to extract thumbnail')
-
- urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
- formats = [{
- 'url': furl,
- 'format_id': determine_ext(furl),
- } for furl in urls]
+ thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
+ sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
+
+ formats = []
+ for source in sources:
+ furl = source.get('src')
+ if furl:
+ formats.append({
+ 'url': furl,
+ 'format_id': determine_ext(furl),
+ })
+ self._sort_formats(formats)
+
return {
'id': episode,
'title': title,
'formats': formats,
- 'thumbnail': poster,
+ 'thumbnail': thumbnail,
}