Import Upstream version 2020.01.24

[youtubedl] / youtube_dl / extractor / udemy.py

diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 195f5ce78d308126a1077cda11a4c00b437343fe..2a4faecefbc271f1f88dfe38d2fe284e0bbd9158 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,


@@ -17,7 +18,9 @@ from ..utils import (
     int_or_none,
     js_to_json,
     sanitized_Request,
     int_or_none,
     js_to_json,
     sanitized_Request,

+    try_get,

     unescapeHTML,
     unescapeHTML,

+    url_or_none,

     urlencode_postdata,
 )
 
     urlencode_postdata,
 )
 


@@ -26,7 +29,7 @@ class UdemyIE(InfoExtractor):
     IE_NAME = 'udemy'
     _VALID_URL = r'''(?x)
                     https?://
     IE_NAME = 'udemy'
     _VALID_URL = r'''(?x)
                     https?://

-                        www\.udemy\.com/
+                        (?:[^/]+\.)?udemy\.com/

                         (?:
                             [^#]+\#/lecture/|
                             lecture/view/?\?lectureId=|
                         (?:
                             [^#]+\#/lecture/|
                             lecture/view/?\?lectureId=|


@@ -57,6 +60,13 @@ class UdemyIE(InfoExtractor):
         # no url in outputs format entry
         'url': 'https://www.udemy.com/learn-web-development-complete-step-by-step-guide-to-success/learn/v4/t/lecture/4125812',
         'only_matching': True,
         # no url in outputs format entry
         'url': 'https://www.udemy.com/learn-web-development-complete-step-by-step-guide-to-success/learn/v4/t/lecture/4125812',
         'only_matching': True,

+    }, {
+        # only outputs rendition
+        'url': 'https://www.udemy.com/how-you-can-help-your-local-community-5-amazing-examples/learn/v4/t/lecture/3225750?start=0',
+        'only_matching': True,
+    }, {
+        'url': 'https://wipro.udemy.com/java-tutorial/#/lecture/172757',
+        'only_matching': True,

     }]
 
     def _extract_course_info(self, webpage, video_id):
     }]
 
     def _extract_course_info(self, webpage, video_id):


@@ -66,7 +76,10 @@ class UdemyIE(InfoExtractor):
                 webpage, 'course', default='{}')),
             video_id, fatal=False) or {}
         course_id = course.get('id') or self._search_regex(
                 webpage, 'course', default='{}')),
             video_id, fatal=False) or {}
         course_id = course.get('id') or self._search_regex(

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


@@ -100,7 +113,7 @@ class UdemyIE(InfoExtractor):
             % (course_id, lecture_id),
             lecture_id, 'Downloading lecture JSON', query={
                 'fields[lecture]': 'title,description,view_html,asset',
             % (course_id, lecture_id),
             lecture_id, 'Downloading lecture JSON', query={
                 'fields[lecture]': 'title,description,view_html,asset',

-                'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
+                'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,stream_urls,captions,data',

             })
 
     def _handle_error(self, response):
             })
 
     def _handle_error(self, response):


@@ -114,6 +127,25 @@ 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_handle(self, *args, **kwargs):
+        headers = kwargs.get('headers', {}).copy()
+        headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
+        kwargs['headers'] = headers
+        ret = super(UdemyIE, self)._download_webpage_handle(
+            *args, **compat_kwargs(kwargs))
+        if not ret:
+            return ret
+        webpage, _ = ret
+        if any(p in webpage for p in (
+                '>Please verify you are a human',
+                'Access to this page has been denied because we believe you are using automation tools to browse the website',
+                '"_pxCaptcha"')):
+            raise ExtractorError(
+                'Udemy asks you to solve a CAPTCHA. Login with browser, '
+                'solve CAPTCHA, then export cookies and pass cookie file to '
+                'youtube-dl with --cookies.', expected=True)
+        return ret
+

     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',


@@ -140,7 +172,7 @@ class UdemyIE(InfoExtractor):
         self._login()
 
     def _login(self):
         self._login()
 
     def _login(self):

-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()

         if username is None:
             return
 
         if username is None:
             return
 


@@ -254,8 +286,8 @@ class UdemyIE(InfoExtractor):
             if not isinstance(source_list, list):
                 return
             for source in source_list:
             if not isinstance(source_list, list):
                 return
             for source in source_list:

-                video_url = source.get('file') or source.get('src')
-                if not video_url or not isinstance(video_url, compat_str):
+                video_url = url_or_none(source.get('file') or source.get('src'))
+                if not video_url:

                     continue
                 if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
                     continue
                 if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(


@@ -282,8 +314,8 @@ class UdemyIE(InfoExtractor):
                     continue
                 if track.get('kind') != 'captions':
                     continue
                     continue
                 if track.get('kind') != 'captions':
                     continue

-                src = track.get('src')
-                if not src or not isinstance(src, compat_str):
+                src = url_or_none(track.get('src'))
+                if not src:

                     continue
                 lang = track.get('language') or track.get(
                     'srclang') or track.get('label')
                     continue
                 lang = track.get('language') or track.get(
                     'srclang') or track.get('label')


@@ -293,9 +325,25 @@ class UdemyIE(InfoExtractor):
                     'url': src,
                 })
 
                     'url': src,
                 })
 

-        download_urls = asset.get('download_urls')
-        if isinstance(download_urls, dict):
-            extract_formats(download_urls.get('Video'))
+        for url_kind in ('download', 'stream'):
+            urls = asset.get('%s_urls' % url_kind)
+            if isinstance(urls, dict):
+                extract_formats(urls.get('Video'))
+
+        captions = asset.get('captions')
+        if isinstance(captions, list):
+            for cc in captions:
+                if not isinstance(cc, dict):
+                    continue
+                cc_url = url_or_none(cc.get('url'))
+                if not cc_url:
+                    continue
+                lang = try_get(cc, lambda x: x['locale']['locale'], compat_str)
+                sub_dict = (automatic_captions if cc.get('source') == 'auto'
+                            else subtitles)
+                sub_dict.setdefault(lang or 'en', []).append({
+                    'url': cc_url,
+                })

 
         view_html = lecture.get('view_html')
         if view_html:
 
         view_html = lecture.get('view_html')
         if view_html:


@@ -330,7 +378,7 @@ class UdemyIE(InfoExtractor):
                     }, res))
 
             # react rendition since 2017.04.15 (see
                     }, res))
 
             # react rendition since 2017.04.15 (see

-            # https://github.com/rg3/youtube-dl/issues/12744)
+            # https://github.com/ytdl-org/youtube-dl/issues/12744)

             data = self._parse_json(
                 self._search_regex(
                     r'videojs-setup-data=(["\'])(?P<data>{.+?})\1', view_html,
             data = self._parse_json(
                 self._search_regex(
                     r'videojs-setup-data=(["\'])(?P<data>{.+?})\1', view_html,


@@ -351,6 +399,12 @@ class UdemyIE(InfoExtractor):
                     fatal=False)
                 extract_subtitles(text_tracks)
 
                     fatal=False)
                 extract_subtitles(text_tracks)
 

+        if not formats and outputs:
+            for format_id, output in outputs.items():
+                f = extract_output_format(output, format_id)
+                if f.get('url'):
+                    formats.append(f)
+

         self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 
         return {
         self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
 
         return {


@@ -367,8 +421,14 @@ class UdemyIE(InfoExtractor):
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'

-    _VALID_URL = r'https?://(?:www\.)?udemy\.com/(?P<id>[^/?#&]+)'
-    _TESTS = []
+    _VALID_URL = r'https?://(?:[^/]+\.)?udemy\.com/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.udemy.com/java-tutorial/',
+        'only_matching': True,
+    }, {
+        'url': 'https://wipro.udemy.com/java-tutorial/',
+        'only_matching': True,
+    }]

 
     @classmethod
     def suitable(cls, url):
 
     @classmethod
     def suitable(cls, url):