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 89b86955913587c3c09474fdffaab8ad338bb26a..2a4faecefbc271f1f88dfe38d2fe284e0bbd9158 100644 (file)
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -5,6 +5,8 @@ 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_urllib_request,
     compat_urlparse,
 )


@@ -14,8 +16,11 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
     ExtractorError,
     float_or_none,
     int_or_none,

+    js_to_json,

     sanitized_Request,
     sanitized_Request,

+    try_get,

     unescapeHTML,
     unescapeHTML,

+    url_or_none,

     urlencode_postdata,
 )
 
     urlencode_postdata,
 )
 


@@ -24,7 +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=|


@@ -51,16 +56,30 @@ class UdemyIE(InfoExtractor):
         # new URL schema
         'url': 'https://www.udemy.com/electric-bass-right-from-the-start/learn/v4/t/lecture/4580906',
         'only_matching': True,
         # new URL schema
         'url': 'https://www.udemy.com/electric-bass-right-from-the-start/learn/v4/t/lecture/4580906',
         '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):
         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+)',
+                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):


@@ -68,7 +87,7 @@ class UdemyIE(InfoExtractor):
             return compat_urlparse.urljoin(base_url, url) if not url.startswith('http') else url
 
         checkout_url = unescapeHTML(self._search_regex(
             return compat_urlparse.urljoin(base_url, url) if not url.startswith('http') else url
 
         checkout_url = unescapeHTML(self._search_regex(

-            r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/payment/checkout/.+?)\1',
+            r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/(?:payment|cart)/checkout/.+?)\1',

             webpage, 'checkout url', group='url', default=None))
         if checkout_url:
             raise ExtractorError(
             webpage, 'checkout url', group='url', default=None))
         if checkout_url:
             raise ExtractorError(


@@ -94,7 +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):


@@ -108,6 +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',


@@ -134,7 +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
 


@@ -158,7 +196,7 @@ 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,


@@ -207,16 +245,19 @@ class UdemyIE(InfoExtractor):
             if youtube_url:
                 return self.url_result(youtube_url, 'Youtube')
 
             if youtube_url:
                 return self.url_result(youtube_url, 'Youtube')
 

-        video_id = asset['id']
+        video_id = compat_str(asset['id'])

         thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
         duration = float_or_none(asset.get('data', {}).get('duration'))
 
         thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
         duration = float_or_none(asset.get('data', {}).get('duration'))
 

+        subtitles = {}
+        automatic_captions = {}
+

         formats = []
 
         formats = []
 

-        def extract_output_format(src):
+        def extract_output_format(src, f_id):

             return {
             return {

-                'url': src['url'],
-                'format_id': '%sp' % (src.get('height') or format_id),
+                'url': src.get('url'),
+                'format_id': '%sp' % (src.get('height') or f_id),

                 'width': int_or_none(src.get('width')),
                 'height': int_or_none(src.get('height')),
                 'vbr': int_or_none(src.get('video_bitrate_in_kbps')),
                 'width': int_or_none(src.get('width')),
                 'height': int_or_none(src.get('height')),
                 'vbr': int_or_none(src.get('video_bitrate_in_kbps')),


@@ -236,30 +277,73 @@ class UdemyIE(InfoExtractor):
         def add_output_format_meta(f, key):
             output = outputs.get(key)
             if isinstance(output, dict):
         def add_output_format_meta(f, key):
             output = outputs.get(key)
             if isinstance(output, dict):

-                output_format = extract_output_format(output)
+                output_format = extract_output_format(output, key)

                 output_format.update(f)
                 return output_format
             return f
 
                 output_format.update(f)
                 return output_format
             return f
 

-        download_urls = asset.get('download_urls')
-        if isinstance(download_urls, dict):
-            video = download_urls.get('Video')
-            if isinstance(video, list):
-                for format_ in video:
-                    video_url = format_.get('file')
-                    if not video_url:
-                        continue
-                    format_id = format_.get('label')
-                    f = {
-                        'url': format_['file'],
-                        'format_id': '%sp' % format_id,
-                        'height': int_or_none(format_id),
-                    }
-                    if format_id:
-                        # Some videos contain additional metadata (e.g.
-                        # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208)
-                        f = add_output_format_meta(f, format_id)
-                    formats.append(f)
+        def extract_formats(source_list):
+            if not isinstance(source_list, list):
+                return
+            for source in source_list:
+                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(
+                        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': '%sp' % format_id,
+                    'height': int_or_none(format_id),
+                }
+                if format_id:
+                    # Some videos contain additional metadata (e.g.
+                    # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208)
+                    f = add_output_format_meta(f, format_id)
+                formats.append(f)
+
+        def extract_subtitles(track_list):
+            if not isinstance(track_list, list):
+                return
+            for track in track_list:
+                if not isinstance(track, dict):
+                    continue
+                if track.get('kind') != 'captions':
+                    continue
+                src = url_or_none(track.get('src'))
+                if not src:
+                    continue
+                lang = track.get('language') or track.get(
+                    'srclang') or track.get('label')
+                sub_dict = automatic_captions if track.get(
+                    'autogenerated') is True else subtitles
+                sub_dict.setdefault(lang, []).append({
+                    'url': src,
+                })
+
+        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:


@@ -293,6 +377,34 @@ class UdemyIE(InfoExtractor):
                         'height': height,
                     }, res))
 
                         'height': height,
                     }, res))
 

+            # react rendition since 2017.04.15 (see
+            # 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,
+                    'setup data', default='{}', group='data'), video_id,
+                transform_source=unescapeHTML, fatal=False)
+            if data and isinstance(data, dict):
+                extract_formats(data.get('sources'))
+                if not duration:
+                    duration = int_or_none(data.get('duration'))
+                extract_subtitles(data.get('tracks'))
+
+            if not subtitles and not automatic_captions:
+                text_tracks = self._parse_json(
+                    self._search_regex(
+                        r'text-tracks=(["\'])(?P<data>\[.+?\])\1', view_html,
+                        'text tracks', default='{}', group='data'), video_id,
+                    transform_source=lambda s: js_to_json(unescapeHTML(s)),
+                    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 {


@@ -301,14 +413,22 @@ class UdemyIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'duration': duration,
             'description': description,
             'thumbnail': thumbnail,
             'duration': duration,

-            'formats': formats
+            'formats': formats,
+            'subtitles': subtitles,
+            'automatic_captions': automatic_captions,

         }
 
 
 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):