cphipps/changedetection.io
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Handle zero-byte/empty content responses with "[ ] Empty pages are a change" option, the same as when the HTML doesnt render any useful text (#2530)

Browse Source
This commit is contained in:
dgtlmoon
2024-07-29 13:27:59 +02:00
committed by GitHub
parent f527744024
commit 8a35d62e02
9 changed files with 75 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
changedetectionio/content_fetchers/playwright.py
View File

@@ -83,7 +83,8 @@ class fetcher(Fetcher):
request_method,
ignore_status_codes=False,
current_include_filters=None,
is_binary=False):
is_binary=False,
empty_pages_are_a_change=False):
from playwright.sync_api import sync_playwright
import playwright._impl._errors
@@ -130,7 +131,7 @@ class fetcher(Fetcher):
if response is None:
context.close()
browser.close()
logger.debug("Content Fetcher > Response object was none")
logger.debug("Content Fetcher > Response object from the browser communication was none")
raise EmptyReply(url=url, status_code=None)
try:
@@ -166,10 +167,10 @@ class fetcher(Fetcher):
raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
if len(self.page.content().strip()) == 0:
if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
context.close()
browser.close()
logger.debug("Content Fetcher > Content was empty")
raise EmptyReply(url=url, status_code=response.status)
# Run Browser Steps here