Skip to content

fix: Python 3.13+ compatibility (cgi removal) and encoding error handling #139

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ravvdevv wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

fix: Python 3.13+ compatibility (cgi removal) and encoding error handling #139

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions dirhunt/crawler_url.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# -*- coding: utf-8 -*-
import cgi
import email.message
import socket

from bs4 import BeautifulSoup
Expand Down Expand Up @@ -71,7 +71,9 @@ def start(self):
self.crawler.results.put(Error(self, e))
self.close()
return self
content_type = cgi.parse_header(resp.headers.get('Content-Type', ''))[0]
ct = email.message.Message()
ct['Content-Type'] = resp.headers.get('Content-Type', '')
content_type = ct.get_content_type()
soup = BeautifulSoup(text, 'html.parser') if content_type == 'text/html' else None
except RequestException as e:
self.crawler.current_processed_count += 1
Expand Down Expand Up @@ -112,7 +114,9 @@ def maybe_rewrite(self):
def must_be_downloaded(self, response):
"""The file must be downloaded to obtain information.
"""
return self.maybe_directory() or (cgi.parse_header(response.headers.get('Content-Type', ''))[0] in [
ct = email.message.Message()
ct['Content-Type'] = response.headers.get('Content-Type', '')
return self.maybe_directory() or (ct.get_content_type() in [
'text/css', 'application/javascript'
])

Expand Down
10 changes: 5 additions & 5 deletions dirhunt/processors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ def search_index_files(self):

def search_keywords(self, text):
if sys.version_info > (3,) and isinstance(text, bytes):
text = text.decode('utf-8')
text = text.decode('utf-8', errors='replace')
for keyword in self.crawler_url.crawler.interesting_keywords:
if keyword in text:
self.keywords_found.add(keyword)
Expand Down Expand Up @@ -252,9 +252,9 @@ class ProcessCssStyleSheet(ProcessBase):

def process(self, text, soup=None):
if sys.version_info > (3,) and isinstance(text, bytes):
text = text.decode('utf-8')
text = text.decode('utf-8', errors='replace')
self.search_keywords(text)
urls = [full_url_address(url, self.crawler_url.url) for url in re.findall(': *url\(["\']?(.+?)["\']?\)', text)]
urls = [full_url_address(url, self.crawler_url.url) for url in re.findall(r'url\([\'"]?(.+?)[\'"]?\)', text)]
for url in urls:
self.add_url(url, depth=0, type='asset')
return urls
Expand All @@ -270,7 +270,7 @@ class ProcessJavaScript(ProcessBase):

def process(self, text, soup=None):
if sys.version_info > (3,) and isinstance(text, bytes):
text = text.decode('utf-8')
text = text.decode('utf-8', errors='replace')
self.search_keywords(text)
urls = [full_url_address(url[0], self.crawler_url.url)
for url in re.findall(TEXT_PLAIN_PATH_STRING_REGEX, text, re.VERBOSE)]
Expand Down Expand Up @@ -426,7 +426,7 @@ def tag_visible(element):
if isinstance(element, Comment):
return False
return True
texts = soup.findAll(text=True)
texts = soup.find_all(string=True)
visible_texts = filter(tag_visible, texts)
for text in visible_texts:
if text.strip():
Expand Down