ContentExtract/module/listpage/pageTurn/1.py

'''
Created on 2019年8月8日

@author: User
'''
import re

if __name__=="__main__":
    main_url = "www.baidu.com/343/acb/36.psp"
    next_page_url = "www.baidu.com/343/ab/1.html"
    print(re.split('(\d+)',main_url))
    main_href = set(re.split('[/|&|?]', main_url))
    tmp_href = set(re.split('[/|&|?]', next_page_url))
    tmp_href_ele1 = list(tmp_href - main_href)
    tmp_href_ele2 = list(main_href - tmp_href)
    print(tmp_href_ele1)
    print(tmp_href_ele2)
    tmp_href_digit_list1 = re.findall(r'\d+', tmp_href_ele1[0])
    tmp_href_digit_list2 = re.findall(r'\d+', tmp_href_ele2[0])
    tmp_href_digit_list = list(set(tmp_href_digit_list1) - set(tmp_href_digit_list2))
    begin = next_page_url.find(tmp_href_ele1[0])
    end = begin + len(tmp_href_ele1[0])
    first_end = next_page_url.find(tmp_href_digit_list[0], begin, end)
    second_begin = first_end + len(tmp_href_digit_list[0])
    first_part = next_page_url[:first_end]
    second_part = next_page_url[second_begin:]
    
    print(first_part,second_part)