From d90df974c3164ea377f2ce2b04742e6ff21379e8 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 16 Dec 2013 22:18:27 +0100 Subject: [academicearth] Add support for courses (#1976) --- youtube_dl/extractor/__init__.py | 3 ++- youtube_dl/extractor/academicearth.py | 36 +++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) create mode 100644 youtube_dl/extractor/academicearth.py (limited to 'youtube_dl') diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2761b5439..7f2f8806e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,6 +1,7 @@ -from .appletrailers import AppleTrailersIE +from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE from .anitube import AnitubeIE +from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE from .ard import ARDIE from .arte import ( diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py new file mode 100644 index 000000000..5045e7332 --- /dev/null +++ b/youtube_dl/extractor/academicearth.py @@ -0,0 +1,36 @@ +import datetime +import json +import re + +from .common import InfoExtractor +from ..utils import ( + remove_start, +) + + +class AcademicEarthCourseIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/courses/(?P[^?#/]+)' + IE_NAME = u'AcademicEarth:Course' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + playlist_id = m.group('id') + + webpage = self._download_webpage(url, playlist_id) + title = self._html_search_regex( + r'

(.*?)

', webpage, u'title') + description = self._html_search_regex( + r'

(.*?)

', + webpage, u'description', fatal=False) + urls = re.findall( + r'

', + webpage) + entries = [self.url_result(u) for u in urls] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': title, + 'description': description, + 'entries': entries, + } -- cgit v1.2.3