diff --git a/changedetectionio/__init__.py b/changedetectionio/__init__.py
index 84fef256..060df7ac 100644
--- a/changedetectionio/__init__.py
+++ b/changedetectionio/__init__.py
@@ -396,18 +396,20 @@ def changedetection_app(config=None, datastore_o=None):
existing_tags = datastore.get_all_tags()
form = forms.quickWatchForm(request.form)
+ webdriver_enabled = True if os.getenv('PLAYWRIGHT_DRIVER_URL', False) or os.getenv('PLAYWRIGHT_DRIVER_URL', False) else False
+
output = render_template("watch-overview.html",
- form=form,
- watches=sorted_watches,
- tags=existing_tags,
active_tag=limit_tag,
app_rss_token=datastore.data['settings']['application']['rss_access_token'],
+ form=form,
+ guid=datastore.data['app_guid'],
has_unviewed=datastore.has_unviewed,
- # Don't link to hosting when we're on the hosting environment
hosted_sticky=os.getenv("SALTED_PASS", False) == False,
- guid=datastore.data['app_guid'],
- queued_uuids=[uuid for p,uuid in update_q.queue])
-
+ queued_uuids=[uuid for p, uuid in update_q.queue],
+ tags=existing_tags,
+ watches=sorted_watches,
+ webdriver_enabled=webdriver_enabled
+ )
if session.get('share-link'):
del(session['share-link'])
@@ -1228,15 +1230,23 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index'))
url = request.form.get('url').strip()
- fetch_processor =request.form.get('fetch_processor').strip()
+
if datastore.url_exists(url):
flash('The URL {} already exists'.format(url), "error")
return redirect(url_for('index'))
add_paused = request.form.get('edit_and_watch_submit_button') != None
+ fetch_processor = request.form.get('fetch_processor')
+
+ extras = {'paused': add_paused}
+ if fetch_processor:
+ extras['fetch_processor']=fetch_processor
+ if fetch_processor == 'image':
+ extras['fetch_backend'] = 'html_webdriver'
+
new_uuid = datastore.add_watch(url=url,
tag=request.form.get('tag').strip(),
- extras={'paused': add_paused, 'fetch_processor': fetch_processor}
+ extras=extras
)
diff --git a/changedetectionio/fetch_processor/__init__.py b/changedetectionio/fetch_processor/__init__.py
index 5bec8922..9c82cb9b 100644
--- a/changedetectionio/fetch_processor/__init__.py
+++ b/changedetectionio/fetch_processor/__init__.py
@@ -1,4 +1,4 @@
-available_fetchers = [('json_html_plaintext', 'JSON/HTML/Text'), ('image', 'Static Image'), ('rendered_webpage', 'Screenshot of page or element')]
+available_fetchers = [('json_html_plaintext', 'JSON/HTML/Text'), ('image', 'Graphically by image or web-page')]
class fetch_processor():
contents = b''
diff --git a/changedetectionio/fetch_processor/image.py b/changedetectionio/fetch_processor/image.py
index ed006601..8f1f1472 100644
--- a/changedetectionio/fetch_processor/image.py
+++ b/changedetectionio/fetch_processor/image.py
@@ -34,6 +34,12 @@ class perform_site_check(fetch_processor):
watch = self.datastore.data['watching'].get(uuid)
+
+ if watch.get('fetch_backend') != 'html_webdriver':
+ raise Exception(
+ "Requires a Chrome compatible fetcher enabled."
+ )
+
# Protect against file:// access
if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
raise Exception(
@@ -80,9 +86,12 @@ class perform_site_check(fetch_processor):
update_obj["last_check_status"] = fetcher.get_last_status_code()
- self.contents = fetcher.raw_content
+ if 'image' in fetcher.headers['content-type']:
+ self.contents = fetcher.raw_content
+ else:
+ self.contents = fetcher.screenshot
- image = Image.open(io.BytesIO(fetcher.raw_content))
+ image = Image.open(io.BytesIO(self.contents))
# @todo different choice?
# https://github.com/JohannesBuchner/imagehash#references
diff --git a/changedetectionio/fetch_processor/rendered_webpage.py b/changedetectionio/fetch_processor/rendered_webpage.py
deleted file mode 100644
index 037b85c3..00000000
--- a/changedetectionio/fetch_processor/rendered_webpage.py
+++ /dev/null
@@ -1,105 +0,0 @@
-import hashlib
-import imagehash
-from PIL import Image
-import io
-import logging
-import os
-import re
-import time
-import urllib3
-
-# fetch processor for requesting and comparing a single image
-# can use both requests and playwright/selenium
-
-# - imagehash for change detection (or https://github.com/dgtlmoon/changedetection.io/pull/419/files#diff-7d3854710a6c0faead783f75850100a4c4b69409309200d3a83692dc9783bf6eR17 ?)
-# - skimage.metrics import structural_similarity for viewing the diff
-
-
-from changedetectionio import content_fetcher, html_tools
-
-urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-
-from . import fetch_processor
-
-
-# Some common stuff here that can be moved to a base class
-# (set_proxy_from_list)
-class perform_site_check(fetch_processor):
- xpath_data = None
-
- def run(self, uuid):
- changed_detected = False
-
- watch = self.datastore.data['watching'].get(uuid)
-
- # Protect against file:// access
- if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
- raise Exception(
- "file:// type access is denied for security reasons."
- )
-
- if watch.get('fetch_backend') != 'html_webdriver':
- raise Exception(
- "Requires a Chrome compatible fetcher enabled."
- )
-
- # Unset any existing notification error
- update_obj = {'last_notification_error': False, 'last_error': False}
-
- extra_headers = self.datastore.data['watching'][uuid].get('headers')
-
- # Tweak the base config with the per-watch ones
- request_headers = self.datastore.data['settings']['headers'].copy()
- request_headers.update(extra_headers)
-
- # https://github.com/psf/requests/issues/4525
- # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
- # do this by accident.
- if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
- request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
-
- timeout = self.datastore.data['settings']['requests']['timeout']
- url = watch.get('url')
- 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)
-
- prefer_backend = watch['fetch_backend']
- if hasattr(content_fetcher, prefer_backend):
- klass = getattr(content_fetcher, prefer_backend)
- else:
- # If the klass doesnt exist, just use a default
- klass = getattr(content_fetcher, "html_requests")
-
- proxy_args = self.set_proxy_from_list(watch)
- fetcher = klass(proxy_override=proxy_args)
-
- fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes)
- fetcher.quit()
-
- # if not image/foobar in mimetype
- # raise content_fecther.NotAnImage(mimetype) ?
- # or better to try load with PIL and catch exception?
-
- update_obj["last_check_status"] = fetcher.get_last_status_code()
-
- self.contents = fetcher.screenshot
-
- image = Image.open(io.BytesIO(fetcher.screenshot))
-
- # @todo different choice?
- # https://github.com/JohannesBuchner/imagehash#references
- fetched_hash = str(imagehash.average_hash(image))
-
- # The main thing that all this at the moment comes down to :)
- if watch['previous_md5'] != fetched_hash:
- changed_detected = True
-
- # Always record the new checksum
- update_obj["previous_md5"] = fetched_hash
-
- # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
- if not watch.get('previous_md5'):
- watch['previous_md5'] = fetched_hash
-
- return changed_detected, update_obj
diff --git a/changedetectionio/templates/watch-overview.html b/changedetectionio/templates/watch-overview.html
index 11dd25fa..817f8ff4 100644
--- a/changedetectionio/templates/watch-overview.html
+++ b/changedetectionio/templates/watch-overview.html
@@ -15,8 +15,10 @@
{{ render_simple_field(form.url, placeholder="https://...", required=true) }}
{{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
+ {% if webdriver_enabled %}
{{ render_field(form.fetch_processor) }}
+ {% endif %}
{{ render_simple_field(form.watch_submit_button, title="Watch this URL!" ) }}