summary refs log tree commit diff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2017-05-28 07:50:15 +0700
committerSergey M․ <dstftw@gmail.com>2017-05-28 07:50:15 +0700
commit855520427458f68076143c4079b038f4d15e5a13 (patch)
treeac3a63107b608b995ac8a08ac8d3bce8d71049f3
parent164fcbfeb75787cfeb1f0a84188ba4c11ac4a009 (diff)
downloadyoutube-dl-855520427458f68076143c4079b038f4d15e5a13.tar.gz
youtube-dl-855520427458f68076143c4079b038f4d15e5a13.tar.xz
youtube-dl-855520427458f68076143c4079b038f4d15e5a13.zip
[xhamster] Extract categories (closes #11728)
-rw-r--r--youtube_dl/extractor/xhamster.py11
1 files changed, 11 insertions, 0 deletions
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 7b6703714..7cf0629e7 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
     dict_get,
     ExtractorError,
     int_or_none,
@@ -25,6 +26,7 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'Ruseful2011',
             'duration': 893,
             'age_limit': 18,
+            'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
         },
     }, {
         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
@@ -36,6 +38,7 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'jojo747400',
             'duration': 200,
             'age_limit': 18,
+            'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
         },
         'params': {
             'skip_download': True,
@@ -51,6 +54,7 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'parejafree',
             'duration': 72,
             'age_limit': 18,
+            'categories': ['Amateur', 'Blowjobs'],
         },
         'params': {
             'skip_download': True,
@@ -152,6 +156,12 @@ class XHamsterIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        categories_html = self._search_regex(
+            r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
+            'categories', default=None)
+        categories = [clean_html(category) for category in re.findall(
+            r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
+
         return {
             'id': video_id,
             'title': title,
@@ -165,6 +175,7 @@ class XHamsterIE(InfoExtractor):
             'dislike_count': int_or_none(dislike_count),
             'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
+            'categories': categories,
             'formats': formats,
         }