From 7bbfac52e9d51ef88625ab90abe4f745c70e64d9 Mon Sep 17 00:00:00 2001
From: rnhmjoj <rnhmjoj@inventati.org>
Date: Tue, 10 Mar 2020 14:33:25 +0100
Subject: [PATCH] handle cookies for tpb http requests

The pirate bay (or a hoster in between) added a mechanism
to rate-limit requests that forces us to handle cookies.
---
 pirate/print.py   | 20 ++++++++++++++++----
 pirate/torrent.py | 11 ++++++++---
 2 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/pirate/print.py b/pirate/print.py
index 55e241d..c7490c2 100644
--- a/pirate/print.py
+++ b/pirate/print.py
@@ -4,12 +4,14 @@ import gzip
 import urllib.parse as parse
 import urllib.request as request
 import shutil
-from io import BytesIO
+
+import pirate.data
 
 import colorama
 import veryprettytable
 
-import pirate.data
+from io import BytesIO
+from http.cookiejar import CookieJar
 
 
 class Printer:
@@ -101,12 +103,17 @@ class Printer:
         self.print(table)
 
     def descriptions(self, chosen_links, results, site):
+        jar = CookieJar()
+        opener = request.build_opener(
+            request.HTTPErrorProcessor,
+            request.HTTPCookieProcessor(jar))
+
         for link in chosen_links:
             path = '/torrent/%s/' % results[link]['id']
             req = request.Request(site + path,
                                   headers=pirate.data.default_headers)
             req.add_header('Accept-encoding', 'gzip')
-            f = request.urlopen(req, timeout=pirate.data.default_timeout)
+            f = opener.open(req, timeout=pirate.data.default_timeout)
 
             if f.info().get('Content-Encoding') == 'gzip':
                 f = gzip.GzipFile(fileobj=BytesIO(f.read()))
@@ -125,13 +132,18 @@ class Printer:
             self.print(desc, color='zebra_0')
 
     def file_lists(self, chosen_links, results, site):
+        jar = CookieJar()
+        opener = request.build_opener(
+            request.HTTPErrorProcessor,
+            request.HTTPCookieProcessor(jar))
+
         for link in chosen_links:
             path = '/ajax_details_filelist.php'
             query = '?id=' + results[link]['id']
             req = request.Request(site + path + query,
                                   headers=pirate.data.default_headers)
             req.add_header('Accept-encoding', 'gzip')
-            f = request.urlopen(req, timeout=pirate.data.default_timeout)
+            f = opener.open(req, timeout=pirate.data.default_timeout)
 
             if f.info().get('Content-Encoding') == 'gzip':
                 f = gzip.GzipFile(fileobj=BytesIO(f.read()))
diff --git a/pirate/torrent.py b/pirate/torrent.py
index 5547463..6e3acc6 100644
--- a/pirate/torrent.py
+++ b/pirate/torrent.py
@@ -7,11 +7,11 @@ import urllib.parse as parse
 import urllib.error
 import os.path
 
-from bs4 import BeautifulSoup
-
 import pirate.data
 
+from bs4 import BeautifulSoup
 from io import BytesIO
+from http.cookiejar import CookieJar
 
 
 parser_regex = r'"(magnet\:\?xt=[^"]*)|<td align="right">([^<]+)</td>'
@@ -152,13 +152,18 @@ def remote(printer, pages, category, sort, mode, terms, mirror):
 
     # Catch the Ctrl-C exception and exit cleanly
     try:
+        jar = CookieJar()
+        opener = request.build_opener(
+            request.HTTPErrorProcessor,
+            request.HTTPCookieProcessor(jar))
+
         for page in range(pages):
             path = build_request_path(page, category, sort, mode, terms)
 
             req = request.Request(mirror + path,
                                   headers=pirate.data.default_headers)
             req.add_header('Accept-encoding', 'gzip')
-            f = request.urlopen(req, timeout=pirate.data.default_timeout)
+            f = opener.open(req, timeout=pirate.data.default_timeout)
             if f.info().get('Content-Encoding') == 'gzip':
                 f = gzip.GzipFile(fileobj=BytesIO(f.read()))
             res = f.read().decode('utf-8')