aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/anysex.py1
-rw-r--r--youtube_dl/extractor/beeg.py4
-rw-r--r--youtube_dl/extractor/eporner.py7
-rw-r--r--youtube_dl/extractor/hornbunny.py30
4 files changed, 27 insertions, 15 deletions
diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py
index 95f23adf1..bc64423a3 100644
--- a/youtube_dl/extractor/anysex.py
+++ b/youtube_dl/extractor/anysex.py
@@ -44,7 +44,6 @@ class AnySexIE(InfoExtractor):
duration = parse_duration(self._search_regex(
r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False))
-
view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index 6f9f4433d..d7301fe18 100644
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -42,7 +42,9 @@ class BeegIE(InfoExtractor):
categories_str = self._html_search_regex(
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
- categories = categories_str.split(',')
+ categories = (
+ None if categories_str is None
+ else categories_str.split(','))
return {
'id': video_id,
diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py
index 33f9ab7a9..6926fcda3 100644
--- a/youtube_dl/extractor/eporner.py
+++ b/youtube_dl/extractor/eporner.py
@@ -36,9 +36,10 @@ class EpornerIE(InfoExtractor):
r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id,
webpage, 'redirect_code')
redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
- webpage2 = self._download_webpage(redirect_url, video_id)
+ player_code = self._download_webpage(
+ redirect_url, video_id, note='Downloading player config')
video_url = self._html_search_regex(
- r'file: "(.*?)",', webpage2, 'video_url')
+ r'file: "(.*?)",', player_code, 'video_url')
duration = parse_duration(self._search_regex(
r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
@@ -53,5 +54,5 @@ class EpornerIE(InfoExtractor):
'title': title,
'duration': duration,
'view_count': view_count,
- 'age_limit': 18,
+ 'age_limit': self._rta_search(webpage),
}
diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py
index d07105d66..7e7714438 100644
--- a/youtube_dl/extractor/hornbunny.py
+++ b/youtube_dl/extractor/hornbunny.py
@@ -4,7 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+ int_or_none,
+ parse_duration,
+)
+
class HornBunnyIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
@@ -24,16 +28,22 @@ class HornBunnyIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
- webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(r'class="title">(.*?)</h2>', webpage, 'title')
- redirect_url = self._html_search_regex(r'pg&settings=(.*?)\|0"\);', webpage, 'title')
+ webpage = self._download_webpage(
+ url, video_id, note='Downloading initial webpage')
+ title = self._html_search_regex(
+ r'class="title">(.*?)</h2>', webpage, 'title')
+ redirect_url = self._html_search_regex(
+ r'pg&settings=(.*?)\|0"\);', webpage, 'title')
webpage2 = self._download_webpage(redirect_url, video_id)
- video_url = self._html_search_regex(r'flvMask:(.*?);', webpage2, 'video_url')
+ video_url = self._html_search_regex(
+ r'flvMask:(.*?);', webpage2, 'video_url')
- mobj = re.search(r'<strong>Runtime:</strong> (?P<minutes>\d+):(?P<seconds>\d+)</div>', webpage)
- duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
-
- view_count = self._html_search_regex(r'<strong>Views:</strong> (\d+)</div>', webpage, 'view count', fatal=False)
+ duration = parse_duration(self._search_regex(
+ r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
+ webpage, 'duration', fatal=False))
+ view_count = int_or_none(self._search_regex(
+ r'<strong>Views:</strong>\s*(\d+)</div>',
+ webpage, 'view count', fatal=False))
return {
'id': video_id,
@@ -41,6 +51,6 @@ class HornBunnyIE(InfoExtractor):
'title': title,
'ext': 'flv',
'duration': duration,
- 'view_count': int_or_none(view_count),
+ 'view_count': view_count,
'age_limit': 18,
}