fulvia/modules/url.py

#!/usr/bin/env python3
"""
URL parsing.
"""
import re
from urllib.parse import urlparse
from html.parser import HTMLParser

import requests

from module import hook, url_callback

HEADERS = {"User-Agent": "bix nood gimme the title", "Range": "bytes=0-4096"}

@url_callback('puu.sh/')
def get_puush_fname(bot, url):
	"""
	Callback puu.sh links. Gets the filename and displays it.
	"""
	try:
		res = requests.head(url)
	except requests.exceptions.RequestException:
		return

	fname = res.headers.get('Content-Disposition', '')
	fname = re.search(r'\"(.*)\"', fname).group(1)
	if not fname:
		return

	bot.msg(f"[ \x0310puu.sh \x03] - \x0304{fname}")


@hook(True)
def title_auto(bot, trigger):
	"""
	Automatically show titles for URLs. For shortened URLs/redirects, find
	where the URL redirects to and show the title for that.
	"""
	if "http" not in ' '.join(trigger.args):
		return
	url_finder = re.compile(r"((?:http|https)(?::\/\/\S+))", re.IGNORECASE)

	urls = re.findall(url_finder, ' '.join(trigger.args))
	if len(urls) == 0:
		return

	for url in urls:
		broken = False
		for key in bot.url_callbacks:
			if key in url:
				bot.url_callbacks[key](bot, url)
				broken = True
		if broken:
			continue
		try:
			res = requests.get(url, headers=HEADERS, verify=True, timeout=10)
		except (requests.exceptions.ConnectionError,
				requests.exceptions.ReadTimeout):
			continue
		try:
			res.raise_for_status()
		except:
			continue
		if not res.headers.get("Content-Type"):
			continue
		if not res.headers.get("Content-Type").startswith("text/html"):
			continue
		if res.text.find("<title>") == -1:
			continue
		title = res.text[res.text.find("<title>")+7:res.text.find("</title>")]
		title = HTMLParser().unescape(title)
		title = title.replace("\n","").strip()
		#title = title.encode("windows_1252").decode("utf-8")
		hostname = urlparse(url).hostname
		bot.msg(f"[ \x0310{title} \x03] - \x0304{hostname}")