[teachable] Extract chapter metadata (closes #24421)

[youtube-dl] / youtube_dl / extractor / teachable.py

diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py
index cca89a4a82fd3f12fff5c83f2c59c26b81db6b0e..290c657543048b4e9f8fcb1dfddb0371f0f3c52f 100644 (file)
--- a/youtube_dl/extractor/teachable.py
+++ b/youtube_dl/extractor/teachable.py
@@ -4,11 +4,12 @@ import re
 
 from .common import InfoExtractor
 from .wistia import WistiaIE
-from ..compat import compat_str
 from ..utils import (
     clean_html,
     ExtractorError,
+    int_or_none,
     get_element_by_class,
+    strip_or_none,
     urlencode_postdata,
     urljoin,
 )
@@ -58,7 +59,7 @@ class TeachableBaseIE(InfoExtractor):
             self._logged_in = True
             return
 
-        login_url = compat_str(urlh.geturl())
+        login_url = urlh.geturl()
 
         login_form = self._hidden_inputs(login_page)
 
@@ -174,11 +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)