From 46ab2846d01793e9f7dc3c196563d953d4d9e7bc Mon Sep 17 00:00:00 2001
From: dgtlmoon <dgtlmoon@gmail.com>
Date: Mon, 22 May 2023 15:38:17 +0200
Subject: [PATCH] Basic headers fetch from file

---
 changedetectionio/__init__.py                 |  1 +
 changedetectionio/model/App.py                | 12 +++++++++
 changedetectionio/model/Watch.py              | 25 +++++++++++++++++++
 .../processors/text_json_diff.py              |  5 ++--
 changedetectionio/store.py                    | 22 +++++++++++++---
 5 files changed, 59 insertions(+), 6 deletions(-)

diff --git a/changedetectionio/__init__.py b/changedetectionio/__init__.py
index 8b3e8e39..d07a52ed 100644
--- a/changedetectionio/__init__.py
+++ b/changedetectionio/__init__.py
@@ -1444,6 +1444,7 @@ def check_for_new_version():
         # Check daily
         app.config.exit.wait(86400)
 
+
 def notification_runner():
     global notification_debug_log
     from datetime import datetime
diff --git a/changedetectionio/model/App.py b/changedetectionio/model/App.py
index 7c7cac9f..54580b3d 100644
--- a/changedetectionio/model/App.py
+++ b/changedetectionio/model/App.py
@@ -49,3 +49,15 @@ class model(dict):
     def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
         self.update(self.base_config)
+
+
+def parse_headers_from_text_file(filepath):
+    headers = {}
+    with open(filepath, 'r') as f:
+        for l in f.readlines():
+            l = l.strip()
+            if not l.startswith('#') and ':' in l:
+                (k, v) = l.split(':')
+                headers[k.strip()] = v.strip()
+
+    return headers
\ No newline at end of file
diff --git a/changedetectionio/model/Watch.py b/changedetectionio/model/Watch.py
index ca654d04..0518dd3d 100644
--- a/changedetectionio/model/Watch.py
+++ b/changedetectionio/model/Watch.py
@@ -473,6 +473,31 @@ class model(dict):
         # None is set
         return False
 
+    def has_extra_headers_file(self):
+        filepath = os.path.join(self.watch_data_dir, 'headers.txt')
+        return os.path.isfile(filepath)
+
+    def get_all_headers(self):
+        from .App import parse_headers_from_text_file
+        headers = self.get('headers', {}).copy()
+        # Available headers on the disk could 'headers.txt' in the watch data dir
+        filepath = os.path.join(self.watch_data_dir, 'headers.txt')
+        try:
+            if os.path.isfile(filepath):
+                headers.update(parse_headers_from_text_file(filepath))
+        except Exception as e:
+            print(f"ERROR reading headers.txt at {filepath}", str(e))
+
+        # Or each by tag, as tagname.txt in the main datadir
+        for f in self.all_tags:
+            fname = re.sub(r'[\W_-]', '', f).lower().strip() + ".txt"
+            filepath = os.path.join(self.__datastore_path, fname)
+            try:
+                if os.path.isfile(filepath):
+                    headers.update(parse_headers_from_text_file(filepath))
+            except Exception as e:
+                print(f"ERROR reading headers.txt at {filepath}", str(e))
+        return headers
 
     def get_last_fetched_before_filters(self):
         import brotli
diff --git a/changedetectionio/processors/text_json_diff.py b/changedetectionio/processors/text_json_diff.py
index cf85522a..f767703b 100644
--- a/changedetectionio/processors/text_json_diff.py
+++ b/changedetectionio/processors/text_json_diff.py
@@ -70,10 +70,9 @@ class perform_site_check(difference_detection_processor):
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        extra_headers = watch.get('headers', [])
-
         # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
+        extra_headers = watch.get_all_headers()
+        request_headers = self.datastore.get_all_headers()
         request_headers.update(extra_headers)
 
         # https://github.com/psf/requests/issues/4525
diff --git a/changedetectionio/store.py b/changedetectionio/store.py
index f69eb907..c5cedbf7 100644
--- a/changedetectionio/store.py
+++ b/changedetectionio/store.py
@@ -3,7 +3,7 @@ from flask import (
 )
 
 from . model import App, Watch
-from copy import deepcopy
+from copy import deepcopy, copy
 from os import path, unlink
 from threading import Lock
 import json
@@ -474,8 +474,6 @@ class ChangeDetectionStore:
         return proxy_list if len(proxy_list) else None
 
 
-
-
     def get_preferred_proxy_for_watch(self, uuid):
         """
         Returns the preferred proxy by ID key
@@ -507,6 +505,24 @@ class ChangeDetectionStore:
 
         return None
 
+    def has_extra_headers_file(self):
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        return os.path.isfile(filepath)
+
+    def get_all_headers(self):
+        from .model.App import parse_headers_from_text_file
+        headers = copy(self.data['settings'].get('headers', {}))
+
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        try:
+            if os.path.isfile(filepath):
+                headers.update(parse_headers_from_text_file(filepath))
+        except Exception as e:
+            print(f"ERROR reading headers.txt at {filepath}", str(e))
+
+        return headers
+
+
     # Run all updates
     # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
     #             So therefor - each `update_n` should be very careful about checking if it needs to actually run