Python3~爬取某公司招聘信息

from urllib import request
from bs4 import BeautifulSoup
import ssl
import json

ssl._create_default_https_context=ssl._create_unverified_context
def bs4_parse(list_obj):

    item_list=[]

    for tr in list_obj:
        item={}#存放数据
        td_list=tr.select('td')

        # 职位名称和href
        # <XXXX>
        #     <a href="http://langlang2017.com">python工程师</a>
        # </XXXX>
        # XXXX.get_text()
        title = td_list[0].get_text()

        # href
        td_square = td_list[0]
        a_list = td_square.select('a')
        a_dic = a_list[0].attrs
        href = a_dic["href"]
        href = "https://hr.tencent.com/" + href

        catalog = td_list[-4].get_text()  # 类别
        num = td_list[-3].get_text()  # 人数
        workPlace = td_list[-2].get_text()  # 工作地点
        publishTime = td_list[-1].get_text()  # 发布时间

        print(title, catalog, num, workPlace, publishTime, href)
        # 存入字典
        item["title"] = title
        item["catalog"] = catalog
        item["num"] = num
        item["workPlace"] = workPlace
        item["publishTime"] = publishTime
        item["href"] = href

        item_list.append(item)
        # print(item)
        data=json.dumps(item_list,ensure_ascii=False)
        #序列号
        with open('tencent.json','a',encoding='utf-8') as f:
            f.write(data)

def tencent(page):
    base_url='https://hr.tencent.com/position.php?keywords=python&start=%s#a'%(page-1)*10
    response = request.urlopen(base_url)
    html = response.read()

    soup = BeautifulSoup(html, 'lxml')
    # print(soup)
    # 奇数行
    tr_list1 = soup.select('tr[class="even"]')
    # 偶数行
    tr_list2 = soup.select('tr[class="odd"]')
    bs4_parse(tr_list1 + tr_list2)

if __name__=='__main__':
    # 抓取前10面的内容
    for page in range(1,11):
        tencent(page)