Use pip conditional requirements to not install playwright for ARM (unsupported)

Dockerfile

@@ -21,12 +21,6 @@ COPY requirements.txt /requirements.txt
 
 RUN pip install --target=/dependencies -r /requirements.txt
 
-# Playwright is an alternative to Selenium
-# Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
-RUN pip install --target=/dependencies playwright~=1.26 \
-    || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
-
-
 RUN pip install --target=/dependencies jq~=1.3 \
     || echo "WARN: Failed to install JQ. The application can still run, but the Jq: filter option will be disabled."
 

README.md

@@ -184,9 +184,9 @@ When you enable a `json:` or `jq:` filter, you can even automatically extract an
 
 `json:$.price` or `jq:.price` would give `23.50`, or you can extract the whole structure
 
-## Proxy configuration
+## Proxy Configuration
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
 
 ## Raspberry Pi support?
 

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

@@ -35,8 +35,6 @@ class perform_site_check():
 
 
     def run(self, uuid):
-        from jinja2 import Environment
-
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
@@ -68,9 +66,7 @@ class perform_site_check():
 
         timeout = self.datastore.data['settings']['requests'].get('timeout')
 
-        # 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())
+        url = watch.link
 
         request_body = self.datastore.data['watching'][uuid].get('body')
         request_method = self.datastore.data['watching'][uuid].get('method')

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
             'body': None,
             'method': 'GET',
@@ -60,7 +62,7 @@ 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']
 
@@ -82,10 +84,19 @@ 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 link(self):
+        url = self.get('url', '')
+        if '{%' in url or '{{' in url:
+            from jinja2 import Environment
+            # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
+            jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+            return str(jinja2_env.from_string(url).render())
+        return url
 
     @property
     def label(self):
@@ -109,18 +120,39 @@ 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):
@@ -132,7 +164,7 @@ 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.
@@ -151,25 +183,19 @@ 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()
@@ -210,14 +236,14 @@ class model(dict):
         return not local_lines.issubset(existing_history)
 
     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
@@ -242,9 +268,14 @@ 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()
@@ -252,7 +283,7 @@ 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/run_all_tests.sh

@@ -46,10 +46,6 @@ unset WEBDRIVER_URL
 docker kill $$-test_selenium
 
 echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
-# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
-PLAYWRIGHT_VERSION=$(grep -i -E "RUN pip install.+" "$SCRIPT_DIR/../Dockerfile" | grep --only-matching -i -E "playwright[=><~+]+[0-9\.]+")
-echo "using $PLAYWRIGHT_VERSION"
-pip3 install "$PLAYWRIGHT_VERSION"
 docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
 # takes a while to spin up
 sleep 5

changedetectionio/static/styles/styles.scss

@@ -156,7 +156,7 @@ body:after, body:before {
 
 .fetch-error {
   padding-top: 1em;
-  font-size: 60%;
+  font-size: 80%;
   max-width: 400px;
   display: block;
 }
@@ -803,4 +803,4 @@ ul {
   padding: 0.5rem;
   border-radius: 5px;
   color: #ff3300;
-}
+}

changedetectionio/templates/watch-overview.html

@@ -87,7 +87,7 @@
                     <a class="state-{{'on' if watch.notification_muted}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications"/></a>
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
-                    <a class="external" target="_blank" rel="noopener" href="{{ watch.url.replace('source:','') }}"></a>
+                    <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
                     <a href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /></a>
 
                     {%if watch.fetch_backend == "html_webdriver" %}<img style="height: 1em; display:inline-block;" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" />{% endif %}

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
+

requirements.txt

@@ -1,36 +1,36 @@
-flask ~= 2.0
+flask~=2.0
 flask_wtf
-eventlet >= 0.31.0
+eventlet>=0.31.0
 validators
-timeago ~= 1.0
-inscriptis ~= 2.2
-feedgen ~= 0.9
-flask-login ~= 0.5
+timeago~=1.0
+inscriptis~=2.2
+feedgen~=0.9
+flask-login~=0.5
 flask_restful
 pytz
 
 # Set these versions together to avoid a RequestsDependencyWarning
 # >= 2.26 also adds Brotli support if brotli is installed
-brotli ~= 1.0
-requests[socks] ~= 2.28
+brotli~=1.0
+requests[socks] ~=2.28
 
-urllib3 > 1.26
-chardet > 2.3.0
+urllib3>1.26
+chardet>2.3.0
 
-wtforms ~= 3.0
-jsonpath-ng ~= 1.5.3
+wtforms~=3.0
+jsonpath-ng~=1.5.3
 
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise ~= 1.1.0
+apprise~=1.1.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
 
 # Pinned version of cryptography otherwise
 # ERROR: Could not build wheels for cryptography which use PEP 517 and cannot be installed directly
-cryptography ~= 3.4
+cryptography~=3.4
 
 # Used for CSS filtering
 bs4
@@ -39,16 +39,17 @@ bs4
 lxml
 
 # 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
-selenium ~= 4.1.0
+selenium~=4.1.0
 
 # https://stackoverflow.com/questions/71652965/importerror-cannot-import-name-safe-str-cmp-from-werkzeug-security/71653849#71653849
 # ImportError: cannot import name 'safe_str_cmp' from 'werkzeug.security'
 # need to revisit flask login versions
-werkzeug ~= 2.0.0
+werkzeug~=2.0.0
 
 # Templating, so far just in the URLs but in the future can be for the notifications also
-jinja2
+jinja2~=3.1
 jinja2-time
 
-# playwright is installed at Dockerfile build time because it's not available on all platforms
+playwright~=1.26; python_version >= "3.8" and "arm" not in platform_machine and "aarch" not in platform_machine
+