lee/changedetection.io
1
0
Fork 0
mirror of https://github.com/dgtlmoon/changedetection.io.git synced 2025-12-04 23:25:32 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

XPath support (#355)

Browse Source 
* XPath support and minor improvements to form validation
This commit is contained in:
dgtlmoon
2022-01-05 17:58:07 +01:00
committed by GitHub
parent f87f7077a6
commit 59d31bf76f
7 changed files with 170 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
changedetectionio/fetch_site_status.py
View File

@@ -114,15 +114,17 @@ class perform_site_check():
if 'json:' in css_filter_rule:
stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, jsonpath_filter=css_filter_rule)
is_html = False
else:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
stripped_text_from_html = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
if is_html:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
html_content = fetcher.content
if has_filter_rule:
html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
# 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)
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)
# get_text() via inscriptis
stripped_text_from_html = get_text(html_content)