Merge a class of geeksforgeeks.com posts into one html, then convert into PDF

merge_multi_html_to_pdf.py

import sys
import requests
from xhtml2pdf import pisa
from bs4 import BeautifulSoup

def convertHtmlToPdf(sourceHtml, outputFilename):
    print "generate pdf to " + outputFilename

    resultFile = open(outputFilename, "w+b")
    pisaStatus = pisa.CreatePDF(
            sourceHtml, 
            dest=resultFile,
            encoding='utf-8')   
    resultFile.close()
    return pisaStatus.err

def fetchPosts(url):
    posts = []

    soup = BeautifulSoup(requests.get(url).content)
    for post in soup.find_all(class_='post-title'):
        posts.append((post.a['href'], post.a['title']))
    
    for page in soup.find_all(class_='page larger'):
        psoup = BeautifulSoup(requests.get(page['href']).content)
        for post in psoup.find_all(class_='post-title'):
            posts.append((post.a['href'], post.a['title']))
    return posts

def postsToPdf(seed_url):
    name = seed_url.split('/')[-2]
    html = "<h1>" + seed_url + "</h1><br>"
    
    posts = fetchPosts(seed_url)
    print "total post number: " + str(len(posts))
    
    for post in posts:
        html += " <br> <a href=\"" + post[0] + "\" target=\"_blank\">" + post[1] + "</a>"
 
    for post in posts:
        print "fetch post: " + post[0]
        try:
            content = BeautifulSoup(requests.get(post[0]).content)
            html += " <br> " + content.find(class_='post-info').prettify()
        except:
            print "Skip Post: " + post[0] + " " + post[1]
    
    f = open(name + ".html", "w")
    f.write(html.encode('utf-8'))
    f.close()

    convertHtmlToPdf(html, name + ".pdf")
    
if __name__=="__main__":
    seed_urls = [
            'http://www.geeksforgeeks.org/tag/dynamic-programming/',
            'http://www.geeksforgeeks.org/tag/advance-data-structures/',
            'http://www.geeksforgeeks.org/tag/Greedy-Algorithm/',
            'http://www.geeksforgeeks.org/tag/backtracking/',
            'http://www.geeksforgeeks.org/tag/pattern-searching/',
            'http://www.geeksforgeeks.org/tag/divide-and-conquer/',
            'http://www.geeksforgeeks.org/tag/MathematicalAlgo/',
            'http://www.geeksforgeeks.org/tag/recursion/',
            'http://www.geeksforgeeks.org/tag/geometric-algorithms/',
            'http://www.geeksforgeeks.org/category/graph/',
            'http://www.geeksforgeeks.org/category/tree/',
            'http://www.geeksforgeeks.org/category/multiple-choice-question/',
            'http://www.geeksforgeeks.org/category/bit-magic/',
            'http://www.geeksforgeeks.org/category/c-strings/',
            ]
    if len(sys.argv) > 1:
        seed_urls = [sys.argv[1]]
    for seed_url in seed_urls:
        postsToPdf(seed_url)