Update upstream source from tag 'upstream/2019.09.28'

[youtubedl] / youtube_dl / extractor / egghead.py

diff --git a/youtube_dl/extractor/egghead.py b/youtube_dl/extractor/egghead.py
index db921465e1c6b14330a7e22be79c7a93c6e6ea7b..df11dc206d29b7938db320d34a0a1a57753ab602 100644 (file)
--- a/youtube_dl/extractor/egghead.py
+++ b/youtube_dl/extractor/egghead.py
@@ -1,20 +1,26 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_str
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    try_get,
+    unified_timestamp,
+    url_or_none,
+)

 
 
 class EggheadCourseIE(InfoExtractor):
     IE_DESC = 'egghead.io course'
     IE_NAME = 'egghead:course'
 
 
 class EggheadCourseIE(InfoExtractor):
     IE_DESC = 'egghead.io course'
     IE_NAME = 'egghead:course'

-    _VALID_URL = r'https://egghead\.io/courses/(?P<id>[a-zA-Z_0-9-]+)'
+    _VALID_URL = r'https://egghead\.io/courses/(?P<id>[^/?#&]+)'

     _TEST = {
         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
         'playlist_count': 29,
         'info_dict': {
     _TEST = {
         'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
         'playlist_count': 29,
         'info_dict': {

-            'id': 'professor-frisby-introduces-composable-functional-javascript',
+            'id': '72',

             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
         },
             'title': 'Professor Frisby Introduces Composable Functional JavaScript',
             'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
         },


@@ -22,18 +28,102 @@ class EggheadCourseIE(InfoExtractor):
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)

-        webpage = self._download_webpage(url, playlist_id)

 
 

-        title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
-        ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
+        lessons = self._download_json(
+            'https://egghead.io/api/v1/series/%s/lessons' % playlist_id,
+            playlist_id, 'Downloading course lessons JSON')
+
+        entries = []
+        for lesson in lessons:
+            lesson_url = url_or_none(lesson.get('http_url'))
+            if not lesson_url:
+                continue
+            lesson_id = lesson.get('id')
+            if lesson_id:
+                lesson_id = compat_str(lesson_id)
+            entries.append(self.url_result(
+                lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
+
+        course = self._download_json(
+            'https://egghead.io/api/v1/series/%s' % playlist_id,
+            playlist_id, 'Downloading course JSON', fatal=False) or {}
+
+        playlist_id = course.get('id')
+        if playlist_id:
+            playlist_id = compat_str(playlist_id)
+
+        return self.playlist_result(
+            entries, playlist_id, course.get('title'),
+            course.get('description'))
+
+
+class EggheadLessonIE(InfoExtractor):
+    IE_DESC = 'egghead.io lesson'
+    IE_NAME = 'egghead:lesson'
+    _VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
+        'info_dict': {
+            'id': '1196',
+            'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
+            'ext': 'mp4',
+            'title': 'Create linear data flow with container style types (Box)',
+            'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
+            'thumbnail': r're:^https?:.*\.jpg$',
+            'timestamp': 1481296768,
+            'upload_date': '20161209',
+            'duration': 304,
+            'view_count': 0,
+            'tags': ['javascript', 'free'],
+        },
+        'params': {
+            'skip_download': True,
+            'format': 'bestvideo',
+        },
+    }, {
+        'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        lesson = self._download_json(
+            'https://egghead.io/api/v1/lessons/%s' % display_id, display_id)
+
+        lesson_id = compat_str(lesson['id'])
+        title = lesson['title']

 
 

-        found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
-        entries = [self.url_result(m) for m in found]
+        formats = []
+        for _, format_url in lesson['media_urls'].items():
+            format_url = url_or_none(format_url)
+            if not format_url:
+                continue
+            ext = determine_ext(format_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, lesson_id, 'mp4', entry_protocol='m3u8',
+                    m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, lesson_id, mpd_id='dash', fatal=False))
+            else:
+                formats.append({
+                    'url': format_url,
+                })
+        self._sort_formats(formats)

 
         return {
 
         return {

-            '_type': 'playlist',
-            'id': playlist_id,
+            'id': lesson_id,
+            'display_id': display_id,

             'title': title,
             'title': title,

-            'description': self._og_search_description(webpage),
-            'entries': entries,
+            'description': lesson.get('summary'),
+            'thumbnail': lesson.get('thumb_nail'),
+            'timestamp': unified_timestamp(lesson.get('published_at')),
+            'duration': int_or_none(lesson.get('duration')),
+            'view_count': int_or_none(lesson.get('plays_count')),
+            'tags': try_get(lesson, lambda x: x['tag_list'], list),
+            'series': try_get(
+                lesson, lambda x: x['series']['title'], compat_str),
+            'formats': formats,

         }
         }