mb/volumetric-regimes-book
1
0
Fork 0
Code Issues 7 Pull Requests Projects Releases Wiki Activity

started with a splitter for h2 headers

Browse Source
This commit is contained in:
manetta 2021-09-08 17:42:03 +02:00
parent 1a0c35dc03
commit a97430278d
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
command-line/update.py
View File

@ -80,6 +80,16 @@ def download_media(html, images, wiki):
return html return html
def split_h2_header(html):
"""
html = string (HTML)
DOES NOT WORK YET!
"""
pattern = '<h2><span class="mw-headline" id=".*?">.*?:.*?</h2>' # split the h2 in two on the ":"
result = re.split(pattern, html)
# print(result[0])
return html
def clean_up(html): def clean_up(html):
""" """
html = string (HTML) html = string (HTML)
@ -103,6 +113,7 @@ def parse_page(pagename, wiki):
images = data['parse']['images'] images = data['parse']['images']
html = download_media(html, images, wiki) html = download_media(html, images, wiki)
html = clean_up(html) html = clean_up(html)
html = split_h2_header(html)
else: else:
html = None html = None