rnhmjoj/pirate-get
1
0
Fork 0
mirror of https://github.com/vikstrous/pirate-get synced 2025-01-10 10:04:21 +01:00
Code Issues Releases Wiki Activity

handle cookies for tpb http requests

Browse Source 
The pirate bay (or a hoster in between) added a mechanism
to rate-limit requests that forces us to handle cookies.
This commit is contained in:
Michele Guerini Rocco 2020-03-10 14:33:25 +01:00
parent 2e1ae8dc59
commit 7bbfac52e9
Signed by: rnhmjoj
GPG Key ID: BFBAF4C975F76450
2 changed files with 24 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
pirate/print.py
View File

@ -4,12 +4,14 @@ import gzip
import urllib.parse as parse import urllib.parse as parse
import urllib.request as request import urllib.request as request
import shutil import shutil
from io import BytesIO
import pirate.data
import colorama import colorama
import veryprettytable import veryprettytable
import pirate.data from io import BytesIO
from http.cookiejar import CookieJar
class Printer: class Printer:
@ -101,12 +103,17 @@ class Printer:
self.print(table) self.print(table)
def descriptions(self, chosen_links, results, site): def descriptions(self, chosen_links, results, site):
jar = CookieJar()
opener = request.build_opener(
request.HTTPErrorProcessor,
request.HTTPCookieProcessor(jar))
for link in chosen_links: for link in chosen_links:
path = '/torrent/%s/' % results[link]['id'] path = '/torrent/%s/' % results[link]['id']
req = request.Request(site + path, req = request.Request(site + path,
headers=pirate.data.default_headers) headers=pirate.data.default_headers)
req.add_header('Accept-encoding', 'gzip') 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': if f.info().get('Content-Encoding') == 'gzip':
f = gzip.GzipFile(fileobj=BytesIO(f.read())) f = gzip.GzipFile(fileobj=BytesIO(f.read()))
@ -125,13 +132,18 @@ class Printer:
self.print(desc, color='zebra_0') self.print(desc, color='zebra_0')
def file_lists(self, chosen_links, results, site): def file_lists(self, chosen_links, results, site):
jar = CookieJar()
opener = request.build_opener(
request.HTTPErrorProcessor,
request.HTTPCookieProcessor(jar))
for link in chosen_links: for link in chosen_links:
path = '/ajax_details_filelist.php' path = '/ajax_details_filelist.php'
query = '?id=' + results[link]['id'] query = '?id=' + results[link]['id']
req = request.Request(site + path + query, req = request.Request(site + path + query,
headers=pirate.data.default_headers) headers=pirate.data.default_headers)
req.add_header('Accept-encoding', 'gzip') 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': if f.info().get('Content-Encoding') == 'gzip':
f = gzip.GzipFile(fileobj=BytesIO(f.read())) f = gzip.GzipFile(fileobj=BytesIO(f.read()))

11
pirate/torrent.py
View File

@ -7,11 +7,11 @@ import urllib.parse as parse
import urllib.error import urllib.error
import os.path import os.path
from bs4 import BeautifulSoup
import pirate.data import pirate.data
from bs4 import BeautifulSoup
from io import BytesIO from io import BytesIO
from http.cookiejar import CookieJar
parser_regex = r'"(magnet\:\?xt=[^"]*)|<td align="right">([^<]+)</td>' 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 # Catch the Ctrl-C exception and exit cleanly
try: try:
jar = CookieJar()
opener = request.build_opener(
request.HTTPErrorProcessor,
request.HTTPCookieProcessor(jar))
for page in range(pages): for page in range(pages):
path = build_request_path(page, category, sort, mode, terms) path = build_request_path(page, category, sort, mode, terms)
req = request.Request(mirror + path, req = request.Request(mirror + path,
headers=pirate.data.default_headers) headers=pirate.data.default_headers)
req.add_header('Accept-encoding', 'gzip') 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': if f.info().get('Content-Encoding') == 'gzip':
f = gzip.GzipFile(fileobj=BytesIO(f.read())) f = gzip.GzipFile(fileobj=BytesIO(f.read()))
res = f.read().decode('utf-8') res = f.read().decode('utf-8')