lee/changedetection.io
1
0
Fork 0
mirror of https://github.com/dgtlmoon/changedetection.io.git synced 2026-09-29 16:56:37 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Try to be more helpful

Browse Source
This commit is contained in:
dgtlmoon
2023-09-26 12:45:41 +02:00
parent 57de4ffe4f
commit 2ff65b53fb
3 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
changedetectionio/content_fetcher.py
+2 -1
View File
@@ -77,11 +77,12 @@ class ScreenshotUnavailable(Exception):
class ReplyWithContentButNoText(Exception):
def __init__(self, status_code, url, screenshot=None):
def __init__(self, status_code, url, screenshot=None, has_filters=False):
# Set this so we can use it in other parts of the app
self.status_code = status_code
self.url = url
self.screenshot = screenshot
self.has_filters = has_filters
return
changedetectionio/processors/text_json_diff.py
+1 -1
View File
@@ -314,7 +314,7 @@ class perform_site_check(difference_detection_processor):
# Treat pages with no renderable text content as a change? No by default
empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot, has_filters=has_filter_rule)
# We rely on the actual text in the html output.. many sites have random script vars etc,
# in the future we'll implement other mechanisms.
changedetectionio/update_worker.py
+5 -1
View File
@@ -251,7 +251,11 @@ class update_worker(threading.Thread):
# Totally fine, it's by choice - just continue on, nothing more to care about
# Page had elements/content but no renderable text
# Backend (not filters) gave zero output
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found (With {} reply code).".format(e.status_code)})
if e.has_filters:
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Got HTML content but no text found (With {e.status_code} reply code), it's possible that the filters you have give an empty result or contain only an image <a href=\"https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images\">more help here</a>"})
else:
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Got HTML content but no text found (With {e.status_code} reply code)."})
if e.screenshot:
self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot)
process_changedetection_results = False