bmc_hub/parse_html.py

25 lines
779 B
Python

import re
with open('app/modules/sag/templates/detail.html', 'r', encoding='utf-8') as f:
content = f.read()
def extract_between(text, start_marker, end_marker):
start = text.find(start_marker)
if start == -1: return "", text
end = text.find(end_marker, start)
if end == -1: return "", text
match = text[start:end+len(end_marker)]
text = text[:start] + text[end+len(end_marker):]
return match, text
def extract_div_by_marker(text, marker):
start = text.find(marker)
if start == -1: return "", text
# find the open div tag nearest to the marker looking backwards
div_start = text.rfind('<div', 0, start)
# wait, sometimes marker is inside the div or before the div.
pass
print("Content loaded, len:", len(content))