boose_magoose/mh_parser
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added note

Browse Source
This commit is contained in:
boose_magoose 2023-11-29 21:27:36 -05:00
parent 7e11f29810
commit 7a48626369
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
xml_parse.py
View File

@ -202,6 +202,15 @@ soup = BeautifulSoup(Path('./vol_1.xml').read_text(), 'xml')
for i in soup.find_all('scripRef'): for i in soup.find_all('scripRef'):
i.clear() i.clear()
# May need to add a loop to look in all <p class='passage> and
# unrap any scripref that is in them. the place Dan is getting confused
# with the book Daniel.
# ??????????
# for passage in soup.find_all('p', class='passage'):
# for ref in passafe.find_all('scripRef'):
# ref.unwrap()
for book in soup.find_all('div1')[2:]: for book in soup.find_all('div1')[2:]:
# this is the folder for the books # this is the folder for the books
print(book.attrs) print(book.attrs)