python爬虫之路（爬取智联招聘信息）

import requests
from bs4 import BeautifulSoup
from multiprocessing import Pool
import re
import time
url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=全国&kw=python&p=1&kt=3'
wbdata = requests.get(url).content
soup = BeautifulSoup(wbdata, 'lxml')
# 搜索到的所有的职位数量
job_count = re.findall(r"共<em>(.*?)</em>个职位满足条件", str(soup))[0]
items = soup.select("div#newlist_list_content_table > table")
# 每页职位信息数量
count = len(items) - 1
print('××××××搜索数据如下××××××：')
print("##职位一共有:",job_count)
print('##每一页职位信息：', count)
# 搜索结果页数
pages = (int(job_count) // count) + 1
print('##一共搜到的页数：', pages)
time.sleep(0.8)
def get_zhaopin(page):
    url = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=全国&kw=python&p={0}&kt=3'.format(page)
    print ("第{0}页".format(page))
    job_name = soup.select("table.newlist > tr > td.zwmc > div > a")
    salarys = soup.select("table.newlist > tr > td.zwyx")
    locations = soup.select("table.newlist > tr > td.gzdd")
    times = soup.select("table.newlist > tr > td.gxsj > span")
    for name, salary, location, time in zip(job_name, salarys, locations, times):
        data = {
            'name': name.get_text(),
            'salary': salary.get_text(),
            'location': location.get_text(),
            'time': time.get_text(),
        }
        print (data)
if __name__ == '__main__':
    pool = Pool(processes=1)
    pool.map_async(get_zhaopin,range(1,pages+1))
    pool.close()
    pool.join()