summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorRemita Amine <[email protected]>2021-04-01 19:03:45 +0100
committerRemita Amine <[email protected]>2021-04-01 19:05:00 +0100
commit04d4a3b136060158438c3f2c1b31c884c6961712 (patch)
tree895aec55a042d1834280a6bdee81e6b2cad805ff
parent392c467f95cbf89114235038e1938c72d97144d9 (diff)
downloadyoutube-dl-04d4a3b136060158438c3f2c1b31c884c6961712.tar.gz
youtube-dl-04d4a3b136060158438c3f2c1b31c884c6961712.zip
[screencastomatic] fix extraction(closes #11976, closes #24489)
-rw-r--r--youtube_dl/extractor/screencastomatic.py48
1 files changed, 31 insertions, 17 deletions
diff --git a/youtube_dl/extractor/screencastomatic.py b/youtube_dl/extractor/screencastomatic.py
index b5e76c9af..0afdc1715 100644
--- a/youtube_dl/extractor/screencastomatic.py
+++ b/youtube_dl/extractor/screencastomatic.py
@@ -2,12 +2,18 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import js_to_json
+from ..utils import (
+ get_element_by_class,
+ int_or_none,
+ remove_start,
+ strip_or_none,
+ unified_strdate,
+)
class ScreencastOMaticIE(InfoExtractor):
- _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)'
- _TEST = {
+ _VALID_URL = r'https?://screencast-o-matic\.com/(?:(?:watch|player)/|embed\?.*?\bsc=)(?P<id>[0-9a-zA-Z]+)'
+ _TESTS = [{
'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl',
'md5': '483583cb80d92588f15ccbedd90f0c18',
'info_dict': {
@@ -16,22 +22,30 @@ class ScreencastOMaticIE(InfoExtractor):
'title': 'Welcome to 3-4 Philosophy @ DECV!',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.',
- 'duration': 369.163,
+ 'duration': 369,
+ 'upload_date': '20141216',
}
- }
+ }, {
+ 'url': 'http://screencast-o-matic.com/player/c2lD3BeOPl',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://screencast-o-matic.com/embed?ff=true&sc=cbV2r4Q5TL&fromPH=true&a=1',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- jwplayer_data = self._parse_json(
- self._search_regex(
- r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", webpage, 'setup code'),
- video_id, transform_source=js_to_json)
-
- info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
- info_dict.update({
- 'title': self._og_search_title(webpage),
- 'description': self._og_search_description(webpage),
+ webpage = self._download_webpage(
+ 'https://screencast-o-matic.com/player/' + video_id, video_id)
+ info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+ info.update({
+ 'id': video_id,
+ 'title': get_element_by_class('overlayTitle', webpage),
+ 'description': strip_or_none(get_element_by_class('overlayDescription', webpage)) or None,
+ 'duration': int_or_none(self._search_regex(
+ r'player\.duration\s*=\s*function\(\)\s*{\s*return\s+(\d+);\s*};',
+ webpage, 'duration', default=None)),
+ 'upload_date': unified_strdate(remove_start(
+ get_element_by_class('overlayPublished', webpage), 'Published: ')),
})
- return info_dict
+ return info