Волков LiveJournal posts parsing

# -*- coding: UTF-8 -*-

import requests
from bs4 import BeautifulSoup
import os, re
import sys, traceback


URLS = [
' salery. livejournal. com/2006',
'salery. livejournal. com/2007' до 2017 г.
]

#тхт файлы
pre = 'C:\\Users\\...\\Desktop\\pre.txt'
post = 'C:\\Users\\...\\Desktop\\post.txt'
links = 'C:\\Users\\...\\Desktop\\links.txt'
linksAndTitles = 'C:\\Users\\...\\Desktop\\linksAndT.txt'
end = 'C:\\Users\\...\\Desktop\\end.txt'

#получаем линки постов жж по месяцам
# salery. livejournal. com/2006/11/ - первая запись в жж была 11 ноября 2006
# salery.livejournal. com /2006/12/
# и т.д.
def preLinks():
    f = open(pre, 'w')
    try:
        for link in URLS:
            r = requests.get(link, 'html.parser')
            soup = BeautifulSoup(r.content, 'html.parser')
            for link in soup.find_all('td', class_='caption', align='right'):
                link2 = link.a.get('href')
                f.write(link2 + '\n')
                print(link2)
    except Exception:
        print(traceback.format_exception(*sys.exc_info())[1])
        input()




def postLinks():
    f = open(pre, 'r')
    f1 = open(post, 'w')
    for i in f:
        print(i)
        r = requests.get(i, 'html.parser')
        soup = BeautifulSoup(r.content, 'html.parser')
        for link in soup.find_all('dt'):
            link2 = link.a.get('href')
            print(link2)
            f1.write(link2 + '\n')
    f.close()
    f1.close()




def linkz():
   f = open(post, 'r')
   f1 = open(links, 'w')
   for i in f:
       print(i)
       r = requests.get(i, 'html.parser')
       soup = BeautifulSoup(r.content, 'html.parser')
       for link in soup.find_all('dt'):
           link2 = link.a.get('href')
           #linkPure = link2.get('href')
           print(link2)
           f1.write(link2 + '\n')




f1 = open(end, 'w') ???
f = open(post, 'r')  ???


def main():
    f1 = open(end, 'w') ????
    f = open(post, 'r') ???
    try:
        for i in f:
            r = requests.get(i, 'html.parser')
            soup = BeautifulSoup(r.content, 'html.parser')
           # post = soup.find('td', colspan='2').text
           # print(post)
        #получаем дату поста, записываем ее
            title = soup.title.text
            print(title)
            f1.write(title + '\n')

        #получаем название поста
            for i in soup.find_all('td', class_="caption post-title"):
                try:
                    name = (i.text)
                    f1.write(name + '\n')
                    print(name)
                except ValueError:
                    print('No name')
                    print(traceback.format_exception(*sys.exc_info())[1])
                    continue

      #получаем линк поста
            for i in soup.find_all('td', align="left", class_="comments", valign="top"):
                link = (i.a.get('href') + '\n')
                f1.write(link)
                f1.write('\n')
                print(link, '\n')

    except Exception:
        print(traceback.format_exception(*sys.exc_info())[1])
        input()

    f1.close()



            #ПОЛУЧАЕМ ТЕКСТ ПОСТА
def text():
    f1 = open(end, 'w')
    f = open('C:\\Users\\....\\Desktop\\Volkov\\end.txt', 'r')
    for i in f:
        f1.write(i)
        match = re.match('http', i)

        if match:
            print(i)
            enter = '\n'
            r = requests.get(i, 'html.parser')
            soup = BeautifulSoup(r.content, 'html.parser')
            t = (soup.find('td', colspan='2').text)

            try:
                print(t)

            except UnicodeError as err:
                print("Error: {0}".format(err))
                continue

            f1.write(t + '\n\n\n\n\n')
    input()


text()

#f1.close()