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

Distill.io JSON export file importer (#592)

Browse Source
This commit is contained in:
dgtlmoon
2022-05-10 17:15:41 +02:00
committed by GitHub
parent 18f0b63b7d
commit f28c260576
7 changed files with 376 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
changedetectionio/fetch_site_status.py
View File

@@ -17,10 +17,10 @@ class perform_site_check():
self.datastore = datastore
# If there was a proxy list enabled, figure out what proxy_args/which proxy to use
# if watch.proxy use that
# fetcher.proxy_override = watch.proxy or main config proxy
# Allows override the proxy on a per-request basis
# ALWAYS use the first one is nothing selected
# if watch.proxy use that
# fetcher.proxy_override = watch.proxy or main config proxy
# Allows override the proxy on a per-request basis
# ALWAYS use the first one is nothing selected
def set_proxy_from_list(self, watch):
proxy_args = None
@@ -149,11 +149,13 @@ class perform_site_check():
# Then we assume HTML
if has_filter_rule:
# For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
if css_filter_rule[0] == '/':
html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule, html_content=fetcher.content)
if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
html_content=fetcher.content)
else:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
if has_subtractive_selectors:
html_content = html_tools.element_removal(subtractive_selectors, html_content)
@@ -173,7 +175,6 @@ class perform_site_check():
# Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
# Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
@@ -224,4 +225,4 @@ class perform_site_check():
if not watch['title'] or not len(watch['title']):
update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot
return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot