aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2020-03-24 02:43:24 +0700
committerSergey M․ <dstftw@gmail.com>2020-03-24 02:57:32 +0700
commit4560adc820a5d4bda5babc62f0f7fc306b13ad86 (patch)
tree4828c01db0e79bd473f319c25de78a09bdb20595
parent63dce3094bf45964b49a2c9f26c94b10cf60c2c2 (diff)
[teachable] Extract chapter metadata (closes #24421)
-rw-r--r--youtube_dl/extractor/teachable.py25
1 files changed, 25 insertions, 0 deletions
diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py
index 4316a6962..290c65754 100644
--- a/youtube_dl/extractor/teachable.py
+++ b/youtube_dl/extractor/teachable.py
@@ -7,7 +7,9 @@ from .wistia import WistiaIE
from ..utils import (
clean_html,
ExtractorError,
+ int_or_none,
get_element_by_class,
+ strip_or_none,
urlencode_postdata,
urljoin,
)
@@ -173,11 +175,34 @@ class TeachableIE(TeachableBaseIE):
title = self._og_search_title(webpage, default=None)
+ chapter = None
+ chapter_number = None
+ section_item = self._search_regex(
+ r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
+ webpage, 'section item', default=None, group='li')
+ if section_item:
+ chapter_number = int_or_none(self._search_regex(
+ r'data-ss-position=["\'](\d+)', section_item, 'section id',
+ default=None))
+ if chapter_number is not None:
+ sections = []
+ for s in re.findall(
+ r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
+ section = strip_or_none(clean_html(s))
+ if not section:
+ sections = []
+ break
+ sections.append(section)
+ if chapter_number <= len(sections):
+ chapter = sections[chapter_number - 1]
+
entries = [{
'_type': 'url_transparent',
'url': wistia_url,
'ie_key': WistiaIE.ie_key(),
'title': title,
+ 'chapter': chapter,
+ 'chapter_number': chapter_number,
} for wistia_url in wistia_urls]
return self.playlist_result(entries, video_id, title)