edward/conference-check
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

User cloudscraper

Browse source
This commit is contained in:
Edward Betts 2025-01-11 16:43:51 +00:00
parent 35c213110d
commit fee54a37e7
1 changed files with 22 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
check.py
View file

@ -2,6 +2,7 @@
"""Check if conference websites are live."""
import html
import os
import re
import smtplib
@ -11,6 +12,7 @@ from email.mime.text import MIMEText
from email.utils import formatdate, make_msgid
from urllib.parse import urlparse, urlunparse
import cloudscraper
import requests
import yaml
from requests.adapters import HTTPAdapter
@ -53,8 +55,14 @@ re_title = re.compile("<title>(.*?)</title>", re.DOTALL)
AGENT = config["browser"]["User-Agent"]
headers = {"User-Agent": AGENT, "Accept": "text/html"}
s = requests.Session()
s.headers.update(headers)
s = cloudscraper.CloudScraper()
s_no_dot = cloudscraper.CloudScraper()
# s = requests.Session()
# s.headers.update(headers)
# s_no_dot = requests.Session()
# s_no_dot.headers.update(headers)
# Create a session and mount the custom adapter for both HTTP and HTTPS requests.
adapter = AbsoluteDNSAdapter()
@ -82,7 +90,7 @@ not_here_list = [
"Ooops! Could Not Find It",
"OpenStreetMap Authentication Proxy",
"Error 404",
"Under Construction",
# "Under Construction",
"Page not found",
"Error 404: Page not found",
"Barcamptools",
@ -95,18 +103,21 @@ not_here_list = [
"This page doesn't currently exist",
"ERROR 503 - Service Unavailable",
"ERROR 503",
"401 Authorization Required",
"Authorization Required",
"used Cloudflare to restrict access",
]
def find_not_here_message(html: str) -> str | None:
def find_not_here_message(page_html: str) -> str | None:
"""Find not here message in web page."""
return next((not_here for not_here in not_here_list if not_here in html), None)
return next((not_here for not_here in not_here_list if not_here in page_html), None)
def get_title(html: str) -> str:
def get_title(page_html: str) -> str:
"""Title from web page."""
m = re_title.search(html)
return m.group(1).strip() if m and m.group(1) else "no title"
m = re_title.search(page_html)
return html.unescape(m.group(1).strip()) if m and m.group(1) else "no title"
def normalize_url(url: str) -> str:
@ -130,9 +141,10 @@ def check_conference(
"""Check if conference is live."""
url = src_url.format(year=year)
past_url = src_url.format(year=year - 1)
no_dot = {"bsideskbh.dk", "pif.camp"}
session = s if all(hostname not in url for hostname in no_dot) else s_no_dot
try:
# SotM Baltics has an invalid TLS certificate, but we don't care
r = s.get(url, verify=False)
r = session.get(url)
except requests.exceptions.ConnectionError:
return (False, "connection refused", None)