Web Strip

#Begin Imports

import os
import urllib.request
from bs4 import BeautifulSoup


#Begin Variables

Blank_Target_URL = "http://www.talesofmu.com/book0x/"
Tags_To_Remove = ["strong","b"]
Allow_Characters = ('_','-')
File_Directory = "Directory\\Path\\"
File_Header = "Test_Header\n\nTestAuthor\n\nBEGIN\n\n"

#Begin Main Loop

for i in range(405, 497):
  soup = BeautifulSoup( urllib.request.urlopen( Blank_Target_URL+str(i) ).read() , "html5lib")
  blank_slate = [s.extract() for s in soup(Tags_To_Remove)]
  blank_slate = ""
  #The below line generates the filename - This could use vars, but I couldn't work out a clean way to do it without rewriting everything.
  currentlistitem = str([s.extract() for s in soup(["h2"])][1]).replace("<h2>","").replace("</h2>","").replace(": ","-").replace(" ","_")
  currentlistitem = "".join(c for c in currentlistitem if c.isalnum() or c in Allow_Characters ).rstrip()
  print(currentlistitem)

  f = open(File_Directory+currentlistitem+".txt", mode="w", errors="ignore")
  f.write(File_Header)

  for row in soup.find_all('div',attrs={"class" : "entry"}):
    f.write(str(row.text).strip().replace("\n","\n\n"))

  f.close()