diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-09-05 22:45:07 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-09-05 22:45:49 +0700 |
| commit | 880fa66f4ffa9afcfce91b5ce39f05909050da67 (patch) | |
| tree | 93674ca897b5cdf59c7980ca2a35cce6e483b4c1 /youtube_dl/extractor/redtube.py | |
| parent | 6348671c4a4e9f45cebc107ff4c148ef4970bb39 (diff) | |
[redtube] Fix formats extraction (closes #14122)
Diffstat (limited to 'youtube_dl/extractor/redtube.py')
| -rw-r--r-- | youtube_dl/extractor/redtube.py | 21 |
1 files changed, 19 insertions, 2 deletions
diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index c367a6ae7..f70a75256 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, @@ -62,7 +63,23 @@ class RedTubeIE(InfoExtractor): 'format_id': format_id, 'height': int_or_none(format_id), }) - else: + medias = self._parse_json( + self._search_regex( + r'mediaDefinition\s*:\s*(\[.+?\])', webpage, + 'media definitions', default='{}'), + video_id, fatal=False) + if medias and isinstance(medias, list): + for media in medias: + format_url = media.get('videoUrl') + if not format_url or not isinstance(format_url, compat_str): + continue + format_id = media.get('quality') + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'height': int_or_none(format_id), + }) + if not formats: video_url = self._html_search_regex( r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL') formats.append({'url': video_url}) @@ -73,7 +90,7 @@ class RedTubeIE(InfoExtractor): r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<', webpage, 'upload date', fatal=False)) duration = int_or_none(self._search_regex( - r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False)) + r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None)) view_count = str_to_int(self._search_regex( r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)', webpage, 'view count', fatal=False)) |