aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorthc202 <thc202@gmail.com>2015-02-27 22:27:30 +0000
committerthc202 <thc202@gmail.com>2015-02-27 22:27:30 +0000
commit40b077bc7ee2722463f23974ce488acb7f11815a (patch)
treea82a5973976eacc0b21d5618c6b4c3fd2f97e310
parentbd3749ed693ae96becd3832f20e765e1efe01476 (diff)
[oppetarkiv] Add new extractor
Some, if not all, of the videos appear to be geo-blocked (Sweden). Test might fail (403 Forbidden) if not run through a Swedish connection.
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/oppetarkiv.py56
2 files changed, 57 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index aecb67bf4..1544f1059 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -350,6 +350,7 @@ from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE
from .ooyala import OoyalaIE
from .openfilm import OpenFilmIE
+from .oppetarkiv import OppetArkivIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
diff --git a/youtube_dl/extractor/oppetarkiv.py b/youtube_dl/extractor/oppetarkiv.py
new file mode 100644
index 000000000..6dd1fad3f
--- /dev/null
+++ b/youtube_dl/extractor/oppetarkiv.py
@@ -0,0 +1,56 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ determine_ext,
+)
+
+
+class OppetArkivIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?oppetarkiv.se/video/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318',
+ 'md5': '7b95ca9bedeead63012b2d7c3992c28f',
+ 'info_dict': {
+ 'id': '1058509',
+ 'ext': 'mp4',
+ 'title': 'Farlig kryssning',
+ 'duration': 2566,
+ 'thumbnail': 're:^https?://.*[\.-]jpg$',
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ info = self._download_json(
+ 'http://www.oppetarkiv.se/video/%s?output=json' % video_id, video_id)
+
+ title = info['context']['title']
+ thumbnail = info['context'].get('thumbnailImage')
+
+ video_info = info['video']
+ formats = []
+ for vr in video_info['videoReferences']:
+ vurl = vr['url']
+ if determine_ext(vurl) == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ vurl, video_id,
+ ext='mp4', entry_protocol='m3u8_native',
+ m3u8_id=vr.get('playerType')))
+ else:
+ formats.append({
+ 'format_id': vr.get('playerType'),
+ 'url': vurl,
+ })
+ self._sort_formats(formats)
+
+ duration = video_info.get('materialLength')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ }