[egghead:course] Fix extraction
This commit is contained in:
parent
a02682fd13
commit
ed84454d35
1 changed files with 7 additions and 9 deletions
|
@ -1,8 +1,6 @@
|
||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
|
||||||
|
|
||||||
|
@ -22,18 +20,18 @@ class EggheadCourseIE(InfoExtractor):
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
playlist_id = self._match_id(url)
|
playlist_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, playlist_id)
|
api_url = 'https://egghead.io/api/v1/series/' + playlist_id
|
||||||
|
course = self._download_json(api_url, playlist_id)
|
||||||
|
title = course.get('title')
|
||||||
|
description = course.get('description')
|
||||||
|
|
||||||
title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
|
lessons = course.get('lessons')
|
||||||
ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
|
entries = [{'_type': 'url', 'ie_key': 'Wistia', 'url': 'wistia:' + l.get('wistia_id')} for l in lessons]
|
||||||
|
|
||||||
found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
|
|
||||||
entries = [self.url_result(m) for m in found]
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'_type': 'playlist',
|
'_type': 'playlist',
|
||||||
'id': playlist_id,
|
'id': playlist_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': self._og_search_description(webpage),
|
'description': description,
|
||||||
'entries': entries,
|
'entries': entries,
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue