debian/patches/remove-autoupdate-mechanism.patch: Remove fewer things to avoid future...

[youtubedl] / youtube_dl / extractor / udemy.py

diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 207c4a6a7ee8131c3e2e5d5823aefb336ad47c47..6d6c0a98fa64e9e2afc68ce2ad569f5a91d5c24b 100644 (file)
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,

+    compat_kwargs,

     compat_str,
     compat_urllib_request,
     compat_urlparse,
     compat_str,
     compat_urllib_request,
     compat_urlparse,


@@ -62,11 +63,11 @@ class UdemyIE(InfoExtractor):
     def _extract_course_info(self, webpage, video_id):
         course = self._parse_json(
             unescapeHTML(self._search_regex(
     def _extract_course_info(self, webpage, video_id):
         course = self._parse_json(
             unescapeHTML(self._search_regex(

-                r'ng-init=["\'].*\bcourse=({.+?});', webpage, 'course', default='{}')),
+                r'ng-init=["\'].*\bcourse=({.+?})[;"\']',
+                webpage, 'course', default='{}')),

             video_id, fatal=False) or {}
         course_id = course.get('id') or self._search_regex(
             video_id, fatal=False) or {}
         course_id = course.get('id') or self._search_regex(

-            (r'"id"\s*:\s*(\d+)', r'data-course-id=["\'](\d+)'),
-            webpage, 'course id')
+            r'data-course-id=["\'](\d+)', webpage, 'course id')

         return course_id, course.get('title')
 
     def _enroll_course(self, base_url, webpage, course_id):
         return course_id, course.get('title')
 
     def _enroll_course(self, base_url, webpage, course_id):


@@ -114,6 +115,11 @@ class UdemyIE(InfoExtractor):
                 error_str += ' - %s' % error_data.get('formErrors')
             raise ExtractorError(error_str, expected=True)
 
                 error_str += ' - %s' % error_data.get('formErrors')
             raise ExtractorError(error_str, expected=True)
 

+    def _download_webpage(self, *args, **kwargs):
+        kwargs.setdefault('headers', {})['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4'
+        return super(UdemyIE, self)._download_webpage(
+            *args, **compat_kwargs(kwargs))
+

     def _download_json(self, url_or_request, *args, **kwargs):
         headers = {
             'X-Udemy-Snail-Case': 'true',
     def _download_json(self, url_or_request, *args, **kwargs):
         headers = {
             'X-Udemy-Snail-Case': 'true',


@@ -164,7 +170,7 @@ class UdemyIE(InfoExtractor):
         })
 
         response = self._download_webpage(
         })
 
         response = self._download_webpage(

-            self._LOGIN_URL, None, 'Logging in as %s' % username,
+            self._LOGIN_URL, None, 'Logging in',

             data=urlencode_postdata(login_form),
             headers={
                 'Referer': self._ORIGIN_URL,
             data=urlencode_postdata(login_form),
             headers={
                 'Referer': self._ORIGIN_URL,


@@ -257,6 +263,11 @@ class UdemyIE(InfoExtractor):
                 video_url = source.get('file') or source.get('src')
                 if not video_url or not isinstance(video_url, compat_str):
                     continue
                 video_url = source.get('file') or source.get('src')
                 if not video_url or not isinstance(video_url, compat_str):
                     continue

+                if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                    continue

                 format_id = source.get('label')
                 f = {
                     'url': video_url,
                 format_id = source.get('label')
                 f = {
                     'url': video_url,