Skip to content

Commit

Permalink
[egghead:course] Add support for egghead.io course playlists
Browse files Browse the repository at this point in the history
Individual egghead videos are already handled by the generic/Wistia extractors.
  • Loading branch information
phihag committed Jan 9, 2017
1 parent e7ea724 commit 8084951
Show file tree
Hide file tree
Showing 3 changed files with 44 additions and 1 deletion.
5 changes: 4 additions & 1 deletion ChangeLog
Original file line number Diff line number Diff line change
@@ -1,3 +1,7 @@
version <unreleased>

+ [egghead:course] Add support for egghead.io courses

version 2017.01.08

Core
Expand All @@ -14,7 +18,6 @@ Extractors
* [comedycentral/mtv] Add support for HLS videos (#11600)
* [discoverygo] Fix JSON data parsing (#11219, #11522)


version 2017.01.05

Extractors
Expand Down
39 changes: 39 additions & 0 deletions youtube_dl/extractor/egghead.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor


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-]+)'
_TEST = {
'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
'playlist_count': 29,
'info_dict': {
'id': 'professor-frisby-introduces-composable-functional-javascript',
'title': 'Professor Frisby Introduces Composable Functional JavaScript',
'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
},
}

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')

found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
entries = [self.url_result(m) for m in found]

return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'description': self._og_search_description(webpage),
'entries': entries,
}
1 change: 1 addition & 0 deletions youtube_dl/extractor/extractors.py
Original file line number Diff line number Diff line change
Expand Up @@ -252,6 +252,7 @@
from .eagleplatform import EaglePlatformIE
from .ebaumsworld import EbaumsWorldIE
from .echomsk import EchoMskIE
from .egghead import EggheadCourseIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
Expand Down

0 comments on commit 8084951

Please sign in to comment.