Created
September 26, 2017 12:04
-
-
Save return0927/474f63500c9c9452a2f6aa865a923ac5 to your computer and use it in GitHub Desktop.
https://tech.microsoft.com parser
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
_URL = "https://technet.microsoft.com/library/security/4010983" | |
import requests, bs4 | |
reqBody = requests.get(_URL) | |
soup = bs4.BeautifulSoup(reqBody.text, "html.parser") | |
_BODY = soup.find("div", attrs={"id":"mainBody"}) | |
_Tags = _BODY.find_all(['h2','p','span']) | |
_Splitter = [] | |
for _TAG in _Tags: | |
_Legacy = _TAG.get_attribute_list("class") | |
if _Legacy == [None]: | |
pass | |
elif _Legacy == ['subheading']: | |
_Splitter.append(_Tags.index(_TAG)) | |
_Result = [] | |
for _INDEX_NO in range( len(_Splitter) ): | |
if _INDEX_NO == len(_Splitter)-1: | |
_Result.append( _Tags[ _Splitter[_INDEX_NO] : ] ) | |
else: | |
_Result.append( _Tags[ _Splitter[_INDEX_NO] : _Splitter[_INDEX_NO+1] ] ) | |
print("\n\n===================================\n\n".join([ "\n".join([ y.text for y in x]) for x in _Result])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment