aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2015-07-22 23:33:28 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2015-07-22 23:33:28 +0800
commit4bb3d999aca4f51e5530a8779ee876c008339609 (patch)
tree8f4cf034186fe2caa510290919978741707d495f
parent70c857b7283270146864f92d159445e038f40781 (diff)
parent40101dc311909523852a88ba69df76be9b6bc920 (diff)
Merge branch 'nichdu-lecture2go'
-rw-r--r--test/test_utils.py1
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/lecture2go.py62
-rw-r--r--youtube_dl/utils.py4
4 files changed, 66 insertions, 2 deletions
diff --git a/test/test_utils.py b/test/test_utils.py
index e13e11b59..65692a9fb 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -324,6 +324,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('02:03:04'), 7384)
self.assertEqual(parse_duration('01:02:03:04'), 93784)
self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
+ self.assertEqual(parse_duration('87 Min.'), 5220)
def test_fix_xml_ampersands(self):
self.assertEqual(
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 50da08830..3cfa804ec 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -275,6 +275,7 @@ from .kuwo import (
)
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
+from .lecture2go import Lecture2GoIE
from .letv import (
LetvIE,
LetvTvIE,
diff --git a/youtube_dl/extractor/lecture2go.py b/youtube_dl/extractor/lecture2go.py
new file mode 100644
index 000000000..40a3d2346
--- /dev/null
+++ b/youtube_dl/extractor/lecture2go.py
@@ -0,0 +1,62 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ determine_ext,
+ parse_duration,
+ int_or_none,
+)
+
+
+class Lecture2GoIE(InfoExtractor):
+ _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473',
+ 'md5': 'ac02b570883020d208d405d5a3fd2f7f',
+ 'info_dict': {
+ 'id': '17473',
+ 'ext': 'flv',
+ 'title': '2 - Endliche Automaten und reguläre Sprachen',
+ 'creator': 'Frank Heitmann',
+ 'duration': 5220,
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title')
+
+ formats = []
+ for url in set(re.findall(r'"src","([^"]+)"', webpage)):
+ ext = determine_ext(url)
+ if ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(url, video_id))
+ elif ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(url, video_id))
+ else:
+ formats.append({
+ 'url': url,
+ })
+
+ self._sort_formats(formats)
+
+ creator = self._html_search_regex(
+ r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator', fatal=False)
+ duration = parse_duration(self._html_search_regex(
+ r'Duration:\s*</em>\s*<em[^>]*>([^<]+)</em>', webpage, 'duration', fatal=False))
+ view_count = int_or_none(self._html_search_regex(
+ r'Views:\s*</em>\s*<em[^>]+>(\d+)</em>', webpage, 'view count', fatal=False))
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'creator': creator,
+ 'duration': duration,
+ 'view_count': view_count,
+ }
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 942f76d24..ae813099d 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1309,10 +1309,10 @@ def parse_duration(s):
m = re.match(
r'''(?ix)(?:P?T)?
(?:
- (?P<only_mins>[0-9.]+)\s*(?:mins?|minutes?)\s*|
+ (?P<only_mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*|
(?P<only_hours>[0-9.]+)\s*(?:hours?)|
- \s*(?P<hours_reversed>[0-9]+)\s*(?:[:h]|hours?)\s*(?P<mins_reversed>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*|
+ \s*(?P<hours_reversed>[0-9]+)\s*(?:[:h]|hours?)\s*(?P<mins_reversed>[0-9]+)\s*(?:[:m]|mins?\.?|minutes?)\s*|
(?:
(?:
(?:(?P<days>[0-9]+)\s*(?:[:d]|days?)\s*)?