python:爬蟲初體驗

最近幫老媽在58上找保姆的工做，無奈58上的中介服務太多 了，我想找一些私人發佈的保姆招聘信息，因此倒騰了一個python的爬蟲，將數據爬出來以後經過Excel進行過濾中介，由於代碼實在是太簡單，這裏就不解釋了

代碼很少，以下：

#!/usr/bin/python
#coding=utf-8


import requests
from bs4 import BeautifulSoup
import xlwt

url1 = "https://gz.58.com/job/pn"
url2 = "/?key=%E4%BF%9D%E5%A7%86&final=1&jump=1&PGTID=0d302408-0000-3bd9-3b86-d29895d9ee5d&ClickID=3"
book = xlwt.Workbook(encoding='utf-8')
sheet = book.add_sheet(u'qingyuan',cell_overwrite_ok=True)
kk = 0

for i in range(1,54):
    print("*******************第"+str(i)+"頁****************************")
    html = requests.get(url1+str(i)+url2)
    soup = BeautifulSoup(html.text, "lxml")

    address = soup.select('#list_con > li.job_item > div.job_title > div.job_name > a > span.address')
    jobTitle = soup.select('#list_con > li.job_item > div.job_title > div.job_name > a > span.name')
    salary = soup.select('#list_con > li.job_item > div.job_title > p.job_salary')
    company = soup.select('#list_con > li.job_item > div.job_comp > div.comp_name > a')
    link = soup.select("#list_con > li.job_item > div.job_title > div.job_name > a")
    if len(address)==0:
        print("*******************第" + i + "頁被攔截****************************")
        break
    for j in range(len(address)):
        sheet.write(j+kk, 0, address[j].get_text())
        sheet.write(j+kk, 1, jobTitle[j].get_text())
        sheet.write(j+kk, 2, salary[j].get_text())
        sheet.write(j+kk, 3, company[j].get('title'))
        sheet.write(j+kk, 4, link[j].get('href'))
    kk = kk+len(address)

path = 'E:/58廣州保姆招聘信息爬蟲結果.xls'
book.save(path)

這是最後排出來的Excel的數據樣子