From 8e8652bbf6a86e61ff9e198a8fefb911c87d163f Mon Sep 17 00:00:00 2001
From: ripe4spite <ripe4spite@tutanota.com>
Date: Sat, 8 Dec 2018 14:54:07 +0000
Subject: [PATCH 1/2] [xhamster] Add XHamsterUserIE

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/xhamster.py   | 58 ++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index e5f18a75d..737edda36 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1406,6 +1406,7 @@ from .xfileshare import XFileShareIE
 from .xhamster import (
     XHamsterIE,
     XHamsterEmbedIE,
+    XHamsterUserIE,
 )
 from .xiami import (
     XiamiSongIE,
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 68a48034e..2c3fa93b9 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
@@ -319,3 +320,60 @@ class XHamsterEmbedIE(InfoExtractor):
             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 
         return self.url_result(video_url, 'XHamster')
+
+
+class XHamsterUserIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/users/(?P<id>[^/]+)/videos/?'
+    _TESTS = [
+        {
+            'note': 'Paginated user profile',
+            'url': 'https://xhamster.com/users/netvideogirls/videos',
+            'playlist_mincount': 267,
+            'info_dict': {
+                'id': 'netvideogirls',
+                'title': 'netvideogirls'
+            }
+        },
+        {
+            'note': 'Non-paginated user profile',
+            'url': 'https://xhamster.com/users/firatkaan/videos',
+            'playlist_mincount': 1,
+            'info_dict': {
+                'id': 'firatkaan',
+                'title': 'firatkaan'
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        videos = []
+
+        for page in itertools.count(1):
+            address = 'https://xhamster.com/users/%s/videos/%d' % (user_id, page)
+            webpage = self._download_webpage(address, user_id, note="Downloading page %d" % page)
+            video_url_matches = re.finditer(r'<a class="video-thumb__image-container thumb-image-container" href="(https://xhamster.com/videos/[^"/]+)" data-sprite', webpage)
+            for video_url_match in video_url_matches:
+                video_url = video_url_match.group(1)
+                videos += [self.url_result(video_url, 'XHamster', '-'.split(video_url)[-1])]
+            if re.search(r'<div class="pager-container"[^>]*>\s*<ul class="no-popunder">\s*</ul>\s*</div>', webpage):
+                # The pager is empty; there is only a single page of results.
+                break
+            next_page_matcher = re.search(r'<a\s+data-page="next"\s+href="([^"]+)">', webpage)
+            if next_page_matcher:
+                # There is a next page.
+                address = next_page_matcher.group(1)
+                continue
+            # Check we can find the previous page button as a sanity check.
+            prev_page_matcher = re.search(r'<a\s+data-page="prev"\s+href="([^"]+)">', webpage)
+            if prev_page_matcher:
+                # No more pages.
+                break
+            raise ExtractorError("Could not correctly parse pagination buttons.")
+
+        return {
+            "_type": "playlist",
+            "entries": videos,
+            "id": user_id,
+            "title": user_id
+        }

From 984a76242de2f4a6525425700f3784db19f3ecf0 Mon Sep 17 00:00:00 2001
From: ripe4spite <ripe4spite@tutanota.com>
Date: Sat, 8 Dec 2018 19:30:06 +0000
Subject: [PATCH 2/2] [xhamster] Attempt to make regular expressions more
 tolerant of page changes.

---
 youtube_dl/extractor/xhamster.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 2c3fa93b9..9ce24172f 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -352,20 +352,20 @@ class XHamsterUserIE(InfoExtractor):
         for page in itertools.count(1):
             address = 'https://xhamster.com/users/%s/videos/%d' % (user_id, page)
             webpage = self._download_webpage(address, user_id, note="Downloading page %d" % page)
-            video_url_matches = re.finditer(r'<a class="video-thumb__image-container thumb-image-container" href="(https://xhamster.com/videos/[^"/]+)" data-sprite', webpage)
+            video_url_matches = re.finditer(r'<a[^>]+class="[^"]*thumb-image-container[^"]*"[^>]+href="(https://xhamster.com/videos/[^"/]+)"', webpage)
             for video_url_match in video_url_matches:
                 video_url = video_url_match.group(1)
                 videos += [self.url_result(video_url, 'XHamster', '-'.split(video_url)[-1])]
-            if re.search(r'<div class="pager-container"[^>]*>\s*<ul class="no-popunder">\s*</ul>\s*</div>', webpage):
+            if re.search(r'<div class="pager-container"[^>]*>\s*<ul[^>]*>\s*</ul>\s*</div>', webpage):
                 # The pager is empty; there is only a single page of results.
                 break
-            next_page_matcher = re.search(r'<a\s+data-page="next"\s+href="([^"]+)">', webpage)
+            next_page_matcher = re.search(r'<a[^>]+data-page="next"[^>]+href="([^"]+)"[^>]*>', webpage)
             if next_page_matcher:
                 # There is a next page.
                 address = next_page_matcher.group(1)
                 continue
             # Check we can find the previous page button as a sanity check.
-            prev_page_matcher = re.search(r'<a\s+data-page="prev"\s+href="([^"]+)">', webpage)
+            prev_page_matcher = re.search(r'<a[^>]+data-page="prev"[^>]+href="([^"]+)"[^>]*>', webpage)
             if prev_page_matcher:
                 # No more pages.
                 break