X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fteachable.py;h=290c657543048b4e9f8fcb1dfddb0371f0f3c52f;hb=4560adc820a5d4bda5babc62f0f7fc306b13ad86;hp=47ac95ee8789ff0ba697cc56625e3a93f2cdded8;hpb=102a4e54c5c0819233773cc15398bc901a218f4c;p=youtube-dl

diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py
index 47ac95ee8..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,
 )
@@ -27,6 +28,7 @@ class TeachableBaseIE(InfoExtractor):
         'market.saleshacker.com': 'saleshacker',
         'learnability.org': 'learnability',
         'edurila.com': 'edurila',
+        'courses.workitdaily.com': 'workitdaily',
     }
 
     _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))
@@ -47,7 +49,17 @@ class TeachableBaseIE(InfoExtractor):
             'https://%s/sign_in' % site, None,
             'Downloading %s login page' % site)
 
-        login_url = compat_str(urlh.geturl())
+        def is_logged(webpage):
+            return any(re.search(p, webpage) for p in (
+                r'class=["\']user-signout',
+                r'<a[^>]+\bhref=["\']/sign_out',
+                r'Log\s+[Oo]ut\s*<'))
+
+        if is_logged(login_page):
+            self._logged_in = True
+            return
+
+        login_url = urlh.geturl()
 
         login_form = self._hidden_inputs(login_page)
 
@@ -77,10 +89,7 @@ class TeachableBaseIE(InfoExtractor):
                 'Go to https://%s/ and accept.' % (site, site), expected=True)
 
         # Successful login
-        if any(re.search(p, response) for p in (
-                r'class=["\']user-signout',
-                r'<a[^>]+\bhref=["\']/sign_out',
-                r'>\s*Log out\s*<')):
+        if is_logged(response):
             self._logged_in = True
             return
 
@@ -152,22 +161,51 @@ 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',
-                    r'id=["\']lecture-locked')):
+                    r'id=["\']lecture-locked',
+                    # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
+                    r'class=["\'](?:inner-)?lesson-locked',
+                    r'>LESSON LOCKED<')):
                 self.raise_login_required('Lecture contents locked')
+            raise ExtractorError('Unable to find video URL')
 
         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):