How to extract contents of inner text of html tag?
Golam Md. Shibly
shiblydu60 at yahoo.com
Sat Mar 1 13:10:58 EST 2014
Hi,
###in.txt
<kbd class="command">
cp -v --remove-destination /usr/share/zoneinfo/
<em class="replaceable"><code><xxx></code></em>
\
/etc/localtime
</kbd>
import sys
import unicodedata
from bs4 import BeautifulSoup
file_name="in.txt"
html_doc=open(file_name,'r')
soup=BeautifulSoup(html_doc)
#print soup.prettify().encode('utf-8')
#file_to_write.writelines( soup.prettify().encode() )
all_kbd=soup.find_all('kbd')
for line in all_kbd:
if line.string == None:
extract_code=line.code.extract().string
#store_code=line.code.decompose()
for inside_line in line:
if "<<" not in inside_line and "EOF" not in inside_line:
if len(inside_line)>0:
print inside_line
print extract_code
expected output:
cp -v --remove-destination /usr/share/zoneinfo/<xxx>\
/etc/localtime
Got output:
cp -v --remove-destination /usr/share/zoneinfo/
None
\
/etc/localtime
None
shibly
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/python-list/attachments/20140301/c24d6f53/attachment.html>
More information about the Python-list
mailing list