From 31e27e23e42b4b9e583fbedcb830676b97fc9f46 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sat, 17 Oct 2015 19:22:47 +0200
Subject: [PATCH 1/9] [youporn] Fixed the extractor by simplifying some parts

---
 youtube_dl/extractor/youporn.py | 32 +++++---------------------------
 1 file changed, 5 insertions(+), 27 deletions(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 4ba7c36db..10961827a 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -27,9 +27,6 @@ class YouPornIE(InfoExtractor):
         'info_dict': {
             'id': '505835',
             'ext': 'mp4',
-            'upload_date': '20101221',
-            'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
-            'uploader': 'Ask Dan And Jennifer',
             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
             'age_limit': 18,
         }
@@ -45,35 +42,20 @@ class YouPornIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
         age_limit = self._rta_search(webpage)
 
-        # Get JSON parameters
-        json_params = self._search_regex(
-            [r'videoJa?son\s*=\s*({.+})',
-             r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'],
-            webpage, 'JSON parameters')
-        try:
-            params = json.loads(json_params)
-        except ValueError:
-            raise ExtractorError('Invalid JSON')
-
         self.report_extraction(video_id)
         try:
-            video_title = params['title']
-            upload_date = unified_strdate(params['release_date_f'])
-            video_description = params['description']
-            video_uploader = params['submitted_by']
-            thumbnail = params['thumbnails'][0]['image']
+            video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL')
         except KeyError:
             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
 
         # Get all of the links from the page
-        DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
-        download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
-                                                webpage, 'download list').strip()
-        LINK_RE = r'<a href="([^"]+)">'
+        DOWNLOAD_LIST_RE = r'(?s)<div id="downloadModal" class="modalBox">(?P<testje>.*?)<div id="embedModal" class="modalBox">'
+        download_list_html = self._search_regex(DOWNLOAD_LIST_RE, webpage, 'testje').strip()
+        LINK_RE = r'<a href=\'([^"]+)\' title=\'Download Video\'>'
         links = re.findall(LINK_RE, download_list_html)
 
         # Get all encrypted links
-        encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
+        encrypted_links = re.findall(r'encryptedQuality[0-9]{3}URL\t=\t\'([a-zA-Z0-9+/]+={0,2})\';', webpage)
         for encrypted_link in encrypted_links:
             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
             links.append(link)
@@ -111,11 +93,7 @@ class YouPornIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'uploader': video_uploader,
-            'upload_date': upload_date,
             'title': video_title,
-            'thumbnail': thumbnail,
-            'description': video_description,
             'age_limit': age_limit,
             'formats': formats,
         }

From f37642289ad0281a63b461153980b048b065b34c Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sat, 17 Oct 2015 22:44:40 +0200
Subject: [PATCH 2/9] [youporn] Added description and thumbnail

---
 youtube_dl/extractor/youporn.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 10961827a..31bc661e5 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -28,6 +28,7 @@ class YouPornIE(InfoExtractor):
             'id': '505835',
             'ext': 'mp4',
             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
+            'description': 'Watch Sex Ed: Is It Safe To Masturbate Daily? at YouPorn.com - YouPorn is the biggest free porn tube site on the net!',
             'age_limit': 18,
         }
     }
@@ -45,6 +46,8 @@ class YouPornIE(InfoExtractor):
         self.report_extraction(video_id)
         try:
             video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL')
+            video_description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', webpage, 'video DESC')
+            video_thumbnail = self._html_search_regex(r'<img src=\'(.+?)\' class="flipbook"', webpage, 'video THUMB')
         except KeyError:
             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
 
@@ -94,6 +97,8 @@ class YouPornIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video_title,
+            'description': video_description,
+            'thumbnail': video_thumbnail,
             'age_limit': age_limit,
             'formats': formats,
         }

From 43ad0eb8f203c87f2a5b150576b49d0b8b161c20 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sun, 18 Oct 2015 10:05:53 +0200
Subject: [PATCH 3/9] [youporn] Added uploader and date

---
 youtube_dl/extractor/youporn.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 31bc661e5..811138547 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -29,6 +29,9 @@ class YouPornIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
             'description': 'Watch Sex Ed: Is It Safe To Masturbate Daily? at YouPorn.com - YouPorn is the biggest free porn tube site on the net!',
+            'uploader': 'Ask Dan And Jennifer',
+            'thumbnail': 'http://cdn5.image.youporn.phncdn.com/201012/17/505835/640x480/8/sex-ed-is-it-safe-to-masturbate-daily-8.jpg',
+            'date': 'December 21, 2010',
             'age_limit': 18,
         }
     }
@@ -46,8 +49,10 @@ class YouPornIE(InfoExtractor):
         self.report_extraction(video_id)
         try:
             video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL')
-            video_description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', webpage, 'video DESC')
-            video_thumbnail = self._html_search_regex(r'<img src=\'(.+?)\' class="flipbook"', webpage, 'video THUMB')
+            video_description = self._html_search_meta('description', webpage, 'video DESC')
+            video_thumbnail = self._html_search_regex(r'page_params.imageurl\t=\t"(.+?)";', webpage, 'video THUMB')
+            video_uploader = self._html_search_regex(r"<div class=\'videoInfoBy\'>By:</div>\n<a href=\"[^>]+\">(.+?)</a>", webpage, 'video UPLOADER')
+            video_date = self._html_search_regex(r"<div class='videoInfoTime'>\n<i class='icon-clock'></i> (.+?)\n</div>", webpage, 'video DATE')
         except KeyError:
             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
 
@@ -99,6 +104,8 @@ class YouPornIE(InfoExtractor):
             'title': video_title,
             'description': video_description,
             'thumbnail': video_thumbnail,
+            'uploader': video_uploader,
+            'date': video_date,
             'age_limit': age_limit,
             'formats': formats,
         }

From 7d9601d6c45ddd5a5330e2c47c440694f51f3d33 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sun, 18 Oct 2015 10:22:52 +0200
Subject: [PATCH 4/9] [youporn] Removed Try and Except lines

---
 youtube_dl/extractor/youporn.py | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 811138547..ac35be13f 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -47,14 +47,11 @@ class YouPornIE(InfoExtractor):
         age_limit = self._rta_search(webpage)
 
         self.report_extraction(video_id)
-        try:
-            video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL')
-            video_description = self._html_search_meta('description', webpage, 'video DESC')
-            video_thumbnail = self._html_search_regex(r'page_params.imageurl\t=\t"(.+?)";', webpage, 'video THUMB')
-            video_uploader = self._html_search_regex(r"<div class=\'videoInfoBy\'>By:</div>\n<a href=\"[^>]+\">(.+?)</a>", webpage, 'video UPLOADER')
-            video_date = self._html_search_regex(r"<div class='videoInfoTime'>\n<i class='icon-clock'></i> (.+?)\n</div>", webpage, 'video DATE')
-        except KeyError:
-            raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
+        video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL')
+        video_description = self._html_search_meta('description', webpage, 'video DESC')
+        video_thumbnail = self._html_search_regex(r'page_params.imageurl\t=\t"(.+?)";', webpage, 'video THUMB')
+        video_uploader = self._html_search_regex(r"<div class=\'videoInfoBy\'>By:</div>\n<a href=\"[^>]+\">(.+?)</a>", webpage, 'video UPLOADER')
+        video_date = self._html_search_regex(r"<div class='videoInfoTime'>\n<i class='icon-clock'></i> (.+?)\n</div>", webpage, 'video DATE')
 
         # Get all of the links from the page
         DOWNLOAD_LIST_RE = r'(?s)<div id="downloadModal" class="modalBox">(?P<testje>.*?)<div id="embedModal" class="modalBox">'

From 4c3bc5ba4e893c062eb1da1684011419c402ade2 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Mon, 19 Oct 2015 20:19:25 +0200
Subject: [PATCH 5/9] [youporn] Fixed date, fatal, formats and /s*

---
 youtube_dl/extractor/youporn.py | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index ac35be13f..3886c1b45 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import json
 import re
 import sys
+import datetime
 
 from .common import InfoExtractor
 from ..compat import (
@@ -31,7 +32,7 @@ class YouPornIE(InfoExtractor):
             'description': 'Watch Sex Ed: Is It Safe To Masturbate Daily? at YouPorn.com - YouPorn is the biggest free porn tube site on the net!',
             'uploader': 'Ask Dan And Jennifer',
             'thumbnail': 'http://cdn5.image.youporn.phncdn.com/201012/17/505835/640x480/8/sex-ed-is-it-safe-to-masturbate-daily-8.jpg',
-            'date': 'December 21, 2010',
+            'date': '20101221',
             'age_limit': 18,
         }
     }
@@ -47,30 +48,22 @@ class YouPornIE(InfoExtractor):
         age_limit = self._rta_search(webpage)
 
         self.report_extraction(video_id)
-        video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL')
-        video_description = self._html_search_meta('description', webpage, 'video DESC')
-        video_thumbnail = self._html_search_regex(r'page_params.imageurl\t=\t"(.+?)";', webpage, 'video THUMB')
-        video_uploader = self._html_search_regex(r"<div class=\'videoInfoBy\'>By:</div>\n<a href=\"[^>]+\">(.+?)</a>", webpage, 'video UPLOADER')
-        video_date = self._html_search_regex(r"<div class='videoInfoTime'>\n<i class='icon-clock'></i> (.+?)\n</div>", webpage, 'video DATE')
+        video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL', fatal=False)
+        video_description = self._html_search_meta('description', webpage, 'video DESC', fatal=False)
+        video_thumbnail = self._html_search_regex(r'page_params.imageurl\t=\t"(.+?)";', webpage, 'video THUMB', fatal=False)
+        video_uploader = self._html_search_regex(r"<div class=\'videoInfoBy\'>By:</div>\n<a href=\"[^>]+\">(.+?)</a>", webpage, 'video UPLOADER', fatal=False)
+        video_date = self._html_search_regex(r"<div class='videoInfoTime'>\n<i class='icon-clock'></i> (.+?)\n</div>", webpage, 'video DATE', fatal=False)
+        video_date = datetime.datetime.strptime(video_date, '%B %d, %Y').strftime('%Y%m%d')
 
         # Get all of the links from the page
-        DOWNLOAD_LIST_RE = r'(?s)<div id="downloadModal" class="modalBox">(?P<testje>.*?)<div id="embedModal" class="modalBox">'
+        DOWNLOAD_LIST_RE = r'(?s)sources: {\n(?P<testje>.*?)}'
         download_list_html = self._search_regex(DOWNLOAD_LIST_RE, webpage, 'testje').strip()
-        LINK_RE = r'<a href=\'([^"]+)\' title=\'Download Video\'>'
+        LINK_RE = r': \'(.+?)\','
         links = re.findall(LINK_RE, download_list_html)
 
-        # Get all encrypted links
-        encrypted_links = re.findall(r'encryptedQuality[0-9]{3}URL\t=\t\'([a-zA-Z0-9+/]+={0,2})\';', webpage)
-        for encrypted_link in encrypted_links:
-            link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
-            links.append(link)
-
         formats = []
         for link in links:
-            # A link looks like this:
-            # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
-            # A path looks like this:
-            # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
+
             video_url = unescapeHTML(link)
             path = compat_urllib_parse_urlparse(video_url).path
             format_parts = path.split('/')[4].split('_')[:2]

From 0fbec61f273cb4eb2a985b3a1e9cd92871286a08 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sat, 24 Oct 2015 22:02:04 +0200
Subject: [PATCH 6/9] [youporn] Undid removing comment about video url
 components & Undid and fixed removal of encrypted URL detection

---
 youtube_dl/extractor/youporn.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 3886c1b45..1f41c882c 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -61,9 +61,18 @@ class YouPornIE(InfoExtractor):
         LINK_RE = r': \'(.+?)\','
         links = re.findall(LINK_RE, download_list_html)
 
+        # Get all encrypted links
+        encrypted_links = re.findall(r'page_params.encryptedQuality[0-9]{3,4}URL\s=\s\'([a-zA-Z0-9+/]+={0,2})\';', webpage)
+        for encrypted_link in encrypted_links:
+            link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
+            links.append(link)
+
         formats = []
         for link in links:
-
+            # A link looks like this:
+            # http://cdn2b.public.youporn.phncdn.com/201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4?rs=200&ri=2500&s=1445599900&e=1445773500&h=5345d19ce9944ec52eb167abf24af248
+            # A path looks like this:
+            # 201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
             video_url = unescapeHTML(link)
             path = compat_urllib_parse_urlparse(video_url).path
             format_parts = path.split('/')[4].split('_')[:2]

From a760a5d15708c18ec832ae862b61f9f334e39f87 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sat, 24 Oct 2015 22:06:08 +0200
Subject: [PATCH 7/9] [youporn] Fix: Add encrypted link to links array only if
 not already in it

---
 youtube_dl/extractor/youporn.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 1f41c882c..420435196 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -65,7 +65,8 @@ class YouPornIE(InfoExtractor):
         encrypted_links = re.findall(r'page_params.encryptedQuality[0-9]{3,4}URL\s=\s\'([a-zA-Z0-9+/]+={0,2})\';', webpage)
         for encrypted_link in encrypted_links:
             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
-            links.append(link)
+            if link not in links:
+                links.append(link)
 
         formats = []
         for link in links:

From fe674c029fb5f423a5ad5417e07f7bf4e4862723 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sat, 24 Oct 2015 22:20:37 +0200
Subject: [PATCH 8/9] [youporn] Fix: Add encrypted link to links array only if
 not already in it

---
 youtube_dl/extractor/youporn.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 420435196..f288f1eeb 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -65,6 +65,7 @@ class YouPornIE(InfoExtractor):
         encrypted_links = re.findall(r'page_params.encryptedQuality[0-9]{3,4}URL\s=\s\'([a-zA-Z0-9+/]+={0,2})\';', webpage)
         for encrypted_link in encrypted_links:
             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
+            # it's unclear if encryted links still differ from normal ones, so only include in links array if it's unique
             if link not in links:
                 links.append(link)
 

From d8826c0bddd8ffb340287b63de8252739d1bb802 Mon Sep 17 00:00:00 2001
From: Erik <erik@vanderleer.nl>
Date: Sun, 25 Oct 2015 09:37:37 +0100
Subject: [PATCH 9/9] [youporn] Fix: cleanup

---
 youtube_dl/extractor/youporn.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index f288f1eeb..546985f3a 100644
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -56,8 +56,8 @@ class YouPornIE(InfoExtractor):
         video_date = datetime.datetime.strptime(video_date, '%B %d, %Y').strftime('%Y%m%d')
 
         # Get all of the links from the page
-        DOWNLOAD_LIST_RE = r'(?s)sources: {\n(?P<testje>.*?)}'
-        download_list_html = self._search_regex(DOWNLOAD_LIST_RE, webpage, 'testje').strip()
+        DOWNLOAD_LIST_RE = r'(?s)sources: {\n(?P<download_list>.*?)}'
+        download_list_html = self._search_regex(DOWNLOAD_LIST_RE, webpage, 'download list').strip()
         LINK_RE = r': \'(.+?)\','
         links = re.findall(LINK_RE, download_list_html)