add custom resolver

2 files changed, 50 insertions, 1 deletions

diff --git a/MyResolver.py b/MyResolver.py
new file mode 100644
index 0000000..cb654ba
--- /dev/null
+++ b/MyResolver.py
@@ -0,0 +1,42 @@
+import requests
+
+class HostHeaderSSLAdapter(requests.adapters.HTTPAdapter):
+    def resolve(self, hostname):
+        import random
+        ips = [
+            '104.16.89.20',  # CloudFlare
+            '151.101.2.109',  # Fastly
+        ]
+        resolutions = {
+            'overpost.biz': random.choice(ips),
+        }
+        return resolutions.get(hostname)
+
+    def send(self, request, **kwargs):
+        from urllib.parse import urlparse
+
+        connection_pool_kwargs = self.poolmanager.connection_pool_kw
+        result = urlparse(request.url)
+        resolved_ip = self.resolve(result.hostname)
+
+        if result.scheme == 'https' and resolved_ip:
+            request.url = request.url.replace(
+                'https://' + result.hostname,
+                'https://' + resolved_ip,
+            )
+            connection_pool_kwargs['server_hostname'] = result.hostname  # SNI
+            connection_pool_kwargs['assert_hostname'] = result.hostname
+
+            # overwrite the host header
+            request.headers['Host'] = result.hostname
+        else:
+            # theses headers from a previous request may have been left
+            connection_pool_kwargs.pop('server_hostname', None)
+            connection_pool_kwargs.pop('assert_hostname', None)
+
+        return super(HostHeaderSSLAdapter, self).send(request, **kwargs)
+
+def get(url: str):
+    session = requests.Session()
+    session.mount('https://', HostHeaderSSLAdapter())
+    return session.get(url)
diff --git a/Overpost.py b/Overpost.py
index cbea1ea..2448319 100644
--- a/Overpost.py
+++ b/Overpost.py
@@ -4,6 +4,7 @@ from re import compile
 import os
 import feedparser
 from dotenv import load_dotenv
+from MyResolver import get
 load_dotenv()
 
 RSS_URL = os.getenv("RSS_URL") or os.path.join(".", "rss.xml")
@@ -64,8 +65,14 @@ def parse_entry(entry): # entry = day
     dict_pop_first_n(links, int(N_LINKS_TO_REMOVE))
     return (datetime.strptime(date, "%d.%m.%Y"), links)
 
+def handle_url(url):
+    if url.startswith("http"):
+        return get(url)
+    else:
+        return url
+
 def get_links(rss_url):
-    feed = feedparser.parse(rss_url)
+    feed = feedparser.parse(handle_url(rss_url))
     return [ parse_entry(entry) for entry in feed.entries ]
 
 def get_newspaper(prefix="", index=0):