X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fteachable.py;h=290c657543048b4e9f8fcb1dfddb0371f0f3c52f;hb=4560adc820a5d4bda5babc62f0f7fc306b13ad86;hp=6b7f13b437e3f3671b355b7dabcea9fd5056969e;hpb=941e359e9512c1c75d42cb5b4b248816e16edb82;p=youtube-dl

diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py
index 6b7f13b43..290c65754 100644
--- 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)
 
@@ -160,8 +161,8 @@ class TeachableIE(TeachableBaseIE):
 
         webpage = self._download_webpage(url, video_id)
 
-        wistia_url = WistiaIE._extract_url(webpage)
-        if not wistia_url:
+        wistia_urls = WistiaIE._extract_urls(webpage)
+        if not wistia_urls:
             if any(re.search(p, webpage) for p in (
                     r'class=["\']lecture-contents-locked',
                     r'>\s*Lecture contents locked',
@@ -174,12 +175,37 @@ class TeachableIE(TeachableBaseIE):
 
         title = self._og_search_title(webpage, default=None)
 
-        return {
+        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)
 
 
 class TeachableCourseIE(TeachableBaseIE):