Goes through a pelican output folder and extracts just the article divs.

extractDivs.py

#!/usr/bin/env python




import poppler, os.path, os, time, datetime
from bs4 import BeautifulSoup

g = open("./output/all.html","w")
x=""
root="./output/"
all = BeautifulSoup(open("./output/index.html"))
p=all.find_all(typ='chapters')



for link in p:
    l = link.get('href')
    chap = BeautifulSoup(open("./output/"+l))
    chaptag=chap.find("article")
    tit=chap.find(id="page-title")
    book=chap.find_all("a",rel="bookmark")
    x=x+"<h1>"+str(tit)+"</h1>"+"<article  style='text-aline:left'>"+str(chaptag)+"</article>"
    if book is not None: 
    	for mark in book:
           l2 = mark.get('href')
           art = BeautifulSoup(open("./output/"+l2[3:]))
           arttag=art.find("article")
           arttit=art.find(id="page-title")
           x=x+"<h2>"+str(arttit)+"</h2>"+"<article  style='text-aline:left'>"+str(arttag)+"</article>"
    	

g.write(x)
g.close