From 4a0132c570e29075e377c8b70d7f61018d1e4479 Mon Sep 17 00:00:00 2001
From: Mathias Rav <rav@cs.au.dk>
Date: Sat, 13 Dec 2014 21:58:52 +0100
Subject: [PATCH 1/2] [Restudy] Add new extractor for restudy.dk
---
youtube_dl/extractor/__init__.py | 1 +
youtube_dl/extractor/restudy.py | 41 ++++++++++++++++++++++++++++++++
2 files changed, 42 insertions(+)
create mode 100644 youtube_dl/extractor/restudy.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 119ec2044..3ae7a8a52 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -316,6 +316,7 @@ from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
+from .restudy import RestudyIE
from .reverbnation import ReverbNationIE
from .ringtv import RingTVIE
from .ro220 import Ro220IE
diff --git a/youtube_dl/extractor/restudy.py b/youtube_dl/extractor/restudy.py
new file mode 100644
index 000000000..56a6c0f93
--- /dev/null
+++ b/youtube_dl/extractor/restudy.py
@@ -0,0 +1,41 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class RestudyIE(InfoExtractor):
+ _VALID_URL = r'https://www.restudy.dk/video/play/id/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'https://www.restudy.dk/video/play/id/1637',
+ # MD5 sum of first 10241 bytes of the video file, as reported by
+ # head -c 10241 Leiden-frosteffekt-1637.mp4 | md5sum
+ 'md5': '4e755c4287f292a1fe5363834a683818',
+ 'info_dict': {
+ 'id': '1637',
+ 'ext': 'mp4',
+ 'title': 'Leiden-frosteffekt',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ xml_url = (
+ 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml'
+ % video_id)
+ xml = self._download_webpage(xml_url, video_id)
+
+ base = self._search_regex(
+ r'<meta base="([^"]+)', xml, 'meta base')
+ # TODO: Provide multiple video qualities instead of forcing highest
+ filename = self._search_regex(
+ r'<video src="mp4:([^"]+_high\.mp4)', xml, 'filename')
+ url = '%s%s' % (base, filename)
+ title = self._og_search_title(webpage)
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': url,
+ 'protocol': 'rtmp',
+ }
From ac265bef1e685706c0be89237117e2df5f796ecb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sun, 14 Dec 2014 03:41:00 +0600
Subject: [PATCH 2/2] [restudy] Simplify and extract all formats
---
youtube_dl/extractor/restudy.py | 37 ++++++++++++++++-----------------
1 file changed, 18 insertions(+), 19 deletions(-)
diff --git a/youtube_dl/extractor/restudy.py b/youtube_dl/extractor/restudy.py
index 56a6c0f93..b17c2bfc0 100644
--- a/youtube_dl/extractor/restudy.py
+++ b/youtube_dl/extractor/restudy.py
@@ -5,37 +5,36 @@ from .common import InfoExtractor
class RestudyIE(InfoExtractor):
- _VALID_URL = r'https://www.restudy.dk/video/play/id/(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.restudy.dk/video/play/id/1637',
- # MD5 sum of first 10241 bytes of the video file, as reported by
- # head -c 10241 Leiden-frosteffekt-1637.mp4 | md5sum
- 'md5': '4e755c4287f292a1fe5363834a683818',
'info_dict': {
'id': '1637',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'Leiden-frosteffekt',
+ 'description': 'Denne video er et eksperiment med flydende kvælstof.',
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
- xml_url = (
- 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml'
- % video_id)
- xml = self._download_webpage(xml_url, video_id)
- base = self._search_regex(
- r'<meta base="([^"]+)', xml, 'meta base')
- # TODO: Provide multiple video qualities instead of forcing highest
- filename = self._search_regex(
- r'<video src="mp4:([^"]+_high\.mp4)', xml, 'filename')
- url = '%s%s' % (base, filename)
- title = self._og_search_title(webpage)
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._og_search_title(webpage).strip()
+ description = self._og_search_description(webpage).strip()
+
+ formats = self._extract_smil_formats(
+ 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id,
+ video_id)
+
return {
'id': video_id,
'title': title,
- 'url': url,
- 'protocol': 'rtmp',
+ 'description': description,
+ 'formats': formats,
}