Add: jpg4 module

comiccrawler/grabber.py

@@ -117,8 +117,7 @@ def do_request(s, url, proxies, retry, **kwargs):
 	sleep_time = 5
 	while True:
 		with get_request_lock(url):
-			r = s.request(kwargs.pop("method", "GET"), url, timeout=(22, 60),
-				 proxies=proxies, **kwargs)
+			r = s.request(kwargs.pop("method", "GET"), url, proxies=proxies, **kwargs)
 		grabber_log(list((r.status_code, r.url, r.request.headers, r.headers) for r in (r.history + [r])))
 
 		if r.status_code in SUCCESS_CODES:

comiccrawler/mods/jpg4.py

@@ -0,0 +1,35 @@
+#! python3
+
+"""
+https://jpg4.su/a/{id}/?sort=date_desc&page=1
+"""
+
+import re
+
+from html import unescape
+
+from ..episode import Episode
+from ..session_manager import session_manager
+
+domain = ["jpg4.su"]
+name = "jpg4"
+noepfolder = True
+
+s = session_manager.get("https://jpg4.su/")
+s.timeout = (22, 180)
+
+def get_title(html, url):
+	title = re.search(r'og:title" content="([^"]+)', html).group(1)
+	return "[jpg4] {}".format(unescape(title).strip())
+
+def get_episodes(html, url):
+	# FIXME: multiple pages?
+	result = []
+	for match in re.finditer(r'<a href="(https://jpg4\.su/img/[^"]+)"[^>]*>\s*<img src="([^"]*)" alt="([^"]*)', html):
+		ep_url, thumb, title = match.groups()
+		title = re.sub(r"\.\w+$", "", title)
+		image = thumb.replace(".md.", ".")
+		result.append(Episode(title, ep_url, image=image))
+
+	return result[::-1]
+

comiccrawler/session_manager.py

@@ -2,7 +2,7 @@
 from threading import Lock
 from typing import Callable, Any
 
-from requests import Session
+from requests import Session as RequestsSession
 
 from .util import extract_curl
 
@@ -16,6 +16,14 @@ def default_key(url: str) -> tuple:
 	r = urlparse(url)
 	return (r.scheme, r.netloc)
 
+class Session(RequestsSession):
+	timeout: Any = (22, 60)
+
+	def request(self, *args, **kwargs):
+		if "timeout" not in kwargs:
+			kwargs["timeout"] = self.timeout
+		return super().request(*args, **kwargs)
+
 class SessionManager:
 	def __init__(self) -> None:
 		self.lock = Lock()