代码1

# coding:utf-8import requestsfrom bs4 import BeautifulSoupfrom multiprocessing import Pooldef 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))    header = {        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36',        'Connection': 'keep-alive',        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' }    wbdata = requests.get(url, headers=header).content    soup = BeautifulSoup(wbdata, 'lxml')    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=5)    pool.map_async(get_zhaopin,range(1, 403+1))    pool.close()    pool.join()

# coding:utf-8import requestsfrom bs4 import BeautifulSoupimport reurl = 'http://sou.zhaopin.com/jobs/searchresult.ashx?jl=全国&kw=python&p=1&kt=3'header = {        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36',        'Connection': 'keep-alive',        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8' }wbdata = requests.get(url, headers=header).contentsoup = BeautifulSoup(wbdata, 'lxml')items = soup.select("div#newlist_list_content_table > table")count = len(items) - 1# 每页职位信息数量print(count)job_count = re.findall(r"共<em>(.*?)</em>个职位满足条件", str(soup))[0]# 搜索结果页数pages = (int(job_count) // count) + 1print(pages)