use custom user agent

acros/models/Host.py

@@ -6,6 +6,8 @@ from PIL import Image
 from django.core.files.base import ContentFile
 from django.db import models
 
+from acros.utils.apis import requests_session
+
 
 class Host(models.Model):
     host = models.CharField(max_length=100)
@@ -21,7 +23,7 @@ class Host(models.Model):
     def save(self, *args, **kwargs):
         if not self.fetched or True:
             with TemporaryFile("rb+") as fd:
-                r = requests.get(f"https://external-content.duckduckgo.com/ip3/{self.host}.ico")
+                r = requests_session.get(f"https://external-content.duckduckgo.com/ip3/{self.host}.ico")
                 if r.ok:
                     filename = self.host + ".png"
                     for chunk in r.iter_content(chunk_size=128):

acros/models/WikipediaImage.py

@@ -4,7 +4,7 @@ import requests
 from django.core.files import File
 from django.db import models
 
-from acros.utils.apis import WikipediaImageAPIObject, NotFoundError
+from acros.utils.apis import WikipediaImageAPIObject, NotFoundError, requests_session
 
 
 class WikipediaImage(models.Model):
@@ -36,7 +36,7 @@ class WikipediaImage(models.Model):
         if filename.endswith(".svg"):
             filename += ".png"
         with TemporaryFile("rb+") as fd:
-            r = requests.get(img.thumburl)
+            r = requests_session.get(img.thumburl)
             for chunk in r.iter_content(chunk_size=128):
                 fd.write(chunk)
             image_file = File(fd)

acros/utils/apis.py

@@ -2,9 +2,20 @@ from typing import Tuple, Optional
 
 import requests
 from bs4 import BeautifulSoup
+from django.core.cache import cache
 
 from acros.utils.html import clean_html, string_to_bool
 
+requests_session = requests.Session()
+commit = cache.get("commit")
+if commit:
+    commit_version = commit[:6]
+else:
+    commit_version = ""
+requests_session.headers.update({
+    "User-Agent": f"Acronomy {commit_version} (https://acronomy.lw1.at)"
+})
+
 
 class NotFoundError(FileNotFoundError):
     """Request could not be found in API"""
@@ -15,7 +26,7 @@ class WikipediaAPISummary:
     urlbase = "https://en.wikipedia.org/api/rest_v1/page/summary/"
 
     def __init__(self, title: str):
-        r = requests.get(self.urlbase + title.replace("/", "%2F"))
+        r = requests_session.get(self.urlbase + title.replace("/", "%2F"))
         try:
             r.raise_for_status()
         except requests.HTTPError:
@@ -50,7 +61,7 @@ class WikipediaAPISummary:
 
 
 def get_website_title(url: str) -> str:
-    r = requests.get(url)
+    r = requests_session.get(url)
     r.raise_for_status()
     soup = BeautifulSoup(r.text, features="html.parser")
     title = soup.find("title")
@@ -61,7 +72,7 @@ class WikipediaImageAPIObject:
     def __init__(self, filename: str):
         self.filename = filename
         print(self.api_url)
-        r = requests.get(self.api_url)
+        r = requests_session.get(self.api_url)
         r.raise_for_status()
         self.data = r.json()
         self.image_obj = list(self.data["query"]["pages"].values())[0]

acros/utils/matomo.py

@@ -3,6 +3,7 @@ from datetime import date
 import requests
 
 from acronomy.settings import MATOMO_API_KEY
+from acros.utils.apis import requests_session
 
 
 def fetch_matomo_pages():
@@ -16,5 +17,5 @@ def fetch_matomo_pages():
           "&method=Actions.getPageUrls" \
           "&module=API" \
           f"&token_auth={MATOMO_API_KEY}"
-    r = requests.get(url)
+    r = requests_session.get(url)
     return r.json()