X-Git-Url: https://git.rapsys.eu/.gitweb.cgi/youtubedl/blobdiff_plain/b238854ce845f3796daac74edab2e8a373e8ba1a..ca4d08063804fb264eb0ae9cc57894198f66e1fb:/youtube_dl/extractor/academicearth.py

diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py
new file mode 100644
index 0000000..ac05f82
--- /dev/null
+++ b/youtube_dl/extractor/academicearth.py
@@ -0,0 +1,31 @@
+import re
+
+from .common import InfoExtractor
+
+
+class AcademicEarthCourseIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
+    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'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+        description = self._html_search_regex(
+            r'<p class="excerpt">(.*?)</p>',
+            webpage, u'description', fatal=False)
+        urls = re.findall(
+            r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+            webpage)
+        entries = [self.url_result(u) for u in urls]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': title,
+            'description': description,
+            'entries': entries,
+        }