Merge branch 'master' into diff-filters

changedetectionio/__init__.py

@@ -987,9 +987,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         # create a ZipFile object
         backupname = "changedetection-backup-{}.zip".format(int(time.time()))
-
-        # We only care about UUIDS from the current index file
-        uuids = list(datastore.data['watching'].keys())
         backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
 
         with zipfile.ZipFile(backup_filepath, "w",
@@ -1005,12 +1002,12 @@ def changedetection_app(config=None, datastore_o=None):
             # Add the flask app secret
             zipObj.write(os.path.join(datastore_o.datastore_path, "secret.txt"), arcname="secret.txt")
 
-            # Add any snapshot data we find, use the full path to access the file, but make the file 'relative' in the Zip.
-            for txt_file_path in Path(datastore_o.datastore_path).rglob('*.txt'):
-                parent_p = txt_file_path.parent
-                if parent_p.name in uuids:
-                    zipObj.write(txt_file_path,
-                                 arcname=str(txt_file_path).replace(datastore_o.datastore_path, ''),
+            # Add any data in the watch data directory.
+            for uuid, w in datastore.data['watching'].items():
+                for f in Path(w.watch_data_dir).glob('*'):
+                    zipObj.write(f,
+                                 # Use the full path to access the file, but make the file 'relative' in the Zip.
+                                 arcname=os.path.join(f.parts[-2], f.parts[-1]),
                                  compress_type=zipfile.ZIP_DEFLATED,
                                  compresslevel=8)
 

changedetectionio/fetch_site_status.py

@@ -36,6 +36,8 @@ class perform_site_check():
 
 
     def run(self, uuid):
+        from jinja2 import Environment
+
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
@@ -79,7 +81,11 @@ class perform_site_check():
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
         timeout = self.datastore.data['settings']['requests'].get('timeout')
-        url = watch.get('url')
+
+        # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
+        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+        url = str(jinja2_env.from_string(watch.get('url')).render())
+
         request_body = self.datastore.data['watching'][uuid].get('body')
         request_method = self.datastore.data['watching'][uuid].get('method')
         ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)

changedetectionio/model/Watch.py

@@ -1,6 +1,8 @@
-import os
-import uuid as uuid_builder
 from distutils.util import strtobool
+import logging
+import os
+import time
+import uuid
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -22,7 +24,7 @@ class model(dict):
             #'newest_history_key': 0,
             'title': None,
             'previous_md5': False,
-            'uuid': str(uuid_builder.uuid4()),
+            'uuid': str(uuid.uuid4()),
             'headers': {},  # Extra headers to send
             'external_header_server': None,  # URL to a server that will return headers
             'body': None,
@@ -63,7 +65,7 @@ class model(dict):
         self.update(self.__base_config)
         self.__datastore_path = kw['datastore_path']
 
-        self['uuid'] = str(uuid_builder.uuid4())
+        self['uuid'] = str(uuid.uuid4())
 
         del kw['datastore_path']
 
@@ -85,10 +87,9 @@ class model(dict):
         return False
 
     def ensure_data_dir_exists(self):
-        target_path = os.path.join(self.__datastore_path, self['uuid'])
-        if not os.path.isdir(target_path):
-            print ("> Creating data dir {}".format(target_path))
-            os.mkdir(target_path)
+        if not os.path.isdir(self.watch_data_dir):
+            print ("> Creating data dir {}".format(self.watch_data_dir))
+            os.mkdir(self.watch_data_dir)
 
     @property
     def label(self):
@@ -112,18 +113,39 @@ class model(dict):
 
     @property
     def history(self):
+        """History index is just a text file as a list
+            {watch-uuid}/history.txt
+
+            contains a list like
+
+            {epoch-time},{filename}\n
+
+            We read in this list as the history information
+
+        """
         tmp_history = {}
-        import logging
-        import time
 
         # Read the history file as a dict
-        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
             logging.debug("Reading history index " + str(time.time()))
             with open(fname, "r") as f:
                 for i in f.readlines():
                     if ',' in i:
                         k, v = i.strip().split(',', 2)
+
+                        # The index history could contain a relative path, so we need to make the fullpath
+                        # so that python can read it
+                        if not '/' in v and not '\'' in v:
+                            v = os.path.join(self.watch_data_dir, v)
+                        else:
+                            # It's possible that they moved the datadir on older versions
+                            # So the snapshot exists but is in a different path
+                            snapshot_fname = v.split('/')[-1]
+                            proposed_new_path = os.path.join(self.watch_data_dir, snapshot_fname)
+                            if not os.path.exists(v) and os.path.exists(proposed_new_path):
+                                v = proposed_new_path
+
                         tmp_history[k] = v
 
         if len(tmp_history):
@@ -135,7 +157,7 @@ class model(dict):
 
     @property
     def has_history(self):
-        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        fname = os.path.join(self.watch_data_dir, "history.txt")
         return os.path.isfile(fname)
 
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
@@ -154,25 +176,19 @@ class model(dict):
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
     def save_history_text(self, contents, timestamp):
-        import uuid
-        import logging
-
-        output_path = os.path.join(self.__datastore_path, self['uuid'])
 
         self.ensure_data_dir_exists()
-        snapshot_fname = os.path.join(output_path, str(uuid.uuid4()))
-
-        logging.debug("Saving history text {}".format(snapshot_fname))
+        snapshot_fname = "{}.txt".format(str(uuid.uuid4()))
 
         # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
         # most sites are utf-8 and some are even broken utf-8
-        with open(snapshot_fname, 'wb') as f:
+        with open(os.path.join(self.watch_data_dir, snapshot_fname), 'wb') as f:
             f.write(contents)
             f.close()
 
         # Append to index
         # @todo check last char was \n
-        index_fname = os.path.join(output_path, "history.txt")
+        index_fname = os.path.join(self.watch_data_dir, "history.txt")
         with open(index_fname, 'a') as f:
             f.write("{},{}\n".format(timestamp, snapshot_fname))
             f.close()
@@ -271,14 +287,14 @@ class model(dict):
         return diff_types
 
     def get_screenshot(self):
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
         if os.path.isfile(fname):
             return fname
 
         return False
 
     def __get_file_ctime(self, filename):
-        fname = os.path.join(self.__datastore_path, self['uuid'], filename)
+        fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
             return int(os.path.getmtime(fname))
         return False
@@ -303,9 +319,14 @@ class model(dict):
     def snapshot_error_screenshot_ctime(self):
         return self.__get_file_ctime('last-error-screenshot.png')
 
+    @property
+    def watch_data_dir(self):
+        # The base dir of the watch data
+        return os.path.join(self.__datastore_path, self['uuid'])
+    
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error.txt")
+        fname = os.path.join(self.watch_data_dir, "last-error.txt")
         if os.path.isfile(fname):
             with open(fname, 'r') as f:
                 return f.read()
@@ -313,7 +334,7 @@ class model(dict):
 
     def get_error_snapshot(self):
         """Return path to the screenshot that resulted in a non-200 error"""
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
         if os.path.isfile(fname):
             return fname
         return False

changedetectionio/templates/edit.html

@@ -40,7 +40,8 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span>
+                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br/>
+                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br/>
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.title, class="m-d") }}

changedetectionio/tests/test_backup.py

@@ -1,18 +1,31 @@
 #!/usr/bin/python3
 
-import time
+from .util import set_original_response, set_modified_response, live_server_setup
 from flask import url_for
 from urllib.request import urlopen
-from . util import set_original_response, set_modified_response, live_server_setup
+from zipfile import ZipFile
+import re
+import time
 
 
 def test_backup(client, live_server):
-
     live_server_setup(live_server)
 
+    set_original_response()
+
     # Give the endpoint time to spin up
     time.sleep(1)
 
+    # Add our URL to the import page
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": url_for('test_endpoint', _external=True)},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    time.sleep(3)
+
     res = client.get(
         url_for("get_backup"),
         follow_redirects=True
@@ -20,6 +33,19 @@ def test_backup(client, live_server):
 
     # Should get the right zip content type
     assert res.content_type == "application/zip"
+
     # Should be PK/ZIP stream
     assert res.data.count(b'PK') >= 2
 
+    # ZipFile from buffer seems non-obvious, just save it instead
+    with open("download.zip", 'wb') as f:
+        f.write(res.data)
+
+    zip = ZipFile('download.zip')
+    l = zip.namelist()
+    uuid4hex = re.compile('^[a-f0-9]{8}-?[a-f0-9]{4}-?4[a-f0-9]{3}-?[89ab][a-f0-9]{3}-?[a-f0-9]{12}.*txt', re.I)
+    newlist = list(filter(uuid4hex.match, l))  # Read Note below
+
+    # Should be two txt files in the archive (history and the snapshot)
+    assert len(newlist) == 2
+

changedetectionio/tests/test_jinja2.py

@@ -0,0 +1,33 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+
+# If there was only a change in the whitespacing, then we shouldnt have a change detected
+def test_jinja2_in_url_query(client, live_server):
+    live_server_setup(live_server)
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_return_query', _external=True)
+
+    # because url_for() will URL-encode the var, but we dont here
+    full_url = "{}?{}".format(test_url,
+                              "date={% now 'Europe/Berlin', '%Y' %}.{% now 'Europe/Berlin', '%m' %}.{% now 'Europe/Berlin', '%d' %}", )
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": full_url, "tag": "test"},
+        follow_redirects=True
+    )
+    assert b"Watch added" in res.data
+    time.sleep(3)
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b'date=2' in res.data

changedetectionio/tests/util.py

@@ -196,5 +196,11 @@ def live_server_setup(live_server):
             return self.app(environ, start_response)
 
     live_server.app.wsgi_app = DefaultCheckboxMiddleware(live_server.app.wsgi_app)
+
+    # Just return some GET var
+    @live_server.app.route('/test-return-query', methods=['GET'])
+    def test_return_query():
+        return request.query_string
+
     live_server.start()
 

requirements.txt

@@ -46,5 +46,9 @@ selenium ~= 4.1.0
 # need to revisit flask login versions
 werkzeug ~= 2.0.0
 
+# Templating, so far just in the URLs but in the future can be for the notifications also
+jinja2
+jinja2-time
+
 # playwright is installed at Dockerfile build time because it's not available on all platforms