[screencastomatic] fix extraction(closes #11976, closes #24489)

pull/28636/head
Remita Amine 2021-04-01 19:03:45 +01:00
parent 392c467f95
commit 04d4a3b136
1 changed files with 31 additions and 17 deletions

View File

@ -2,12 +2,18 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor 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): class ScreencastOMaticIE(InfoExtractor):
_VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)' _VALID_URL = r'https?://screencast-o-matic\.com/(?:(?:watch|player)/|embed\?.*?\bsc=)(?P<id>[0-9a-zA-Z]+)'
_TEST = { _TESTS = [{
'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl', 'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl',
'md5': '483583cb80d92588f15ccbedd90f0c18', 'md5': '483583cb80d92588f15ccbedd90f0c18',
'info_dict': { 'info_dict': {
@ -16,22 +22,30 @@ class ScreencastOMaticIE(InfoExtractor):
'title': 'Welcome to 3-4 Philosophy @ DECV!', 'title': 'Welcome to 3-4 Philosophy @ DECV!',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.', '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): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(
'https://screencast-o-matic.com/player/' + video_id, video_id)
jwplayer_data = self._parse_json( info = self._parse_html5_media_entries(url, webpage, video_id)[0]
self._search_regex( info.update({
r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", webpage, 'setup code'), 'id': video_id,
video_id, transform_source=js_to_json) 'title': get_element_by_class('overlayTitle', webpage),
'description': strip_or_none(get_element_by_class('overlayDescription', webpage)) or None,
info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False) 'duration': int_or_none(self._search_regex(
info_dict.update({ r'player\.duration\s*=\s*function\(\)\s*{\s*return\s+(\d+);\s*};',
'title': self._og_search_title(webpage), webpage, 'duration', default=None)),
'description': self._og_search_description(webpage), 'upload_date': unified_strdate(remove_start(
get_element_by_class('overlayPublished', webpage), 'Published: ')),
}) })
return info_dict return info