Skip to content

Replace cgi content type parsing #136

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

Draft
Mirochill wants to merge 1 commit into
base: develop
Choose a base branch
from
+16 −4
Draft

Replace cgi content type parsing #136

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
14 changes: 11 additions & 3 deletions dirhunt/crawler_url.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
import cgi
import socket
from email.message import Message

from bs4 import BeautifulSoup
from requests import RequestException
Expand All @@ -17,6 +17,14 @@
}


def parse_content_type(content_type):
if not content_type:
return ''
message = Message()
message['content-type'] = content_type
return message.get_content_type()


class CrawlerUrl(object):
def __init__(self, crawler, url, depth=3, source=None, exists=None, type=None, timeout=10):
"""
Expand Down Expand Up @@ -71,7 +79,7 @@ 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]
content_type = parse_content_type(resp.headers.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 +120,7 @@ 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 [
return self.maybe_directory() or (parse_content_type(response.headers.get('Content-Type', '')) in [
'text/css', 'application/javascript'
])

Expand Down
6 changes: 5 additions & 1 deletion dirhunt/tests/test_crawler_url.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,17 @@
import requests
import requests_mock

from dirhunt.crawler_url import CrawlerUrl
from dirhunt.crawler_url import CrawlerUrl, parse_content_type
from dirhunt.tests.base import CrawlerTestBase

from dirhunt.tests._compat import patch, Mock


class TestCrawlerUrl(CrawlerTestBase, unittest.TestCase):
def test_parse_content_type(self):
self.assertEqual(parse_content_type('text/html; charset=utf-8'), 'text/html')
self.assertEqual(parse_content_type(''), '')

def test_start(self):
crawler = self.get_crawler()
crawler.closing = False
Expand Down