本爬蟲主要使用了requests缴啡、json阶冈、bs4(BeautifulSoup)等相關(guān)模塊解藻，不完善之處請大家不吝賜教孝治！:)
出處：https://github.com/jingsupo/python-spider/blob/master/day04/04tencent_hr.py

# -*- coding:utf-8 -*-

import requests, json, time
from bs4 import BeautifulSoup


class tencent_hr(object):
    def __init__(self):
        self.base_url = "http://hr.tencent.com/position.php?"
        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"}
        self.item_list = []
        self.page = 0

    # 發(fā)送請求
    def send_request(self, url, params={}):
        time.sleep(2)
        try:
            response = requests.get(url, params=params, headers=self.headers)
            return response.content
        except Exception as e:
            print e

    # 解析數(shù)據(jù)
    def parse_data(self, data):
        # 初始化
        bs = BeautifulSoup(data, 'lxml')

        # 獲取標簽-結(jié)果為列表
        data_list = bs.select('.even, .odd')

        # 將結(jié)果中的每一行數(shù)據(jù)提取出來
        for data in data_list:
            data_dict = {}
            data_dict['work_name'] = data.select('td a')[0].get_text()
            data_dict['work_type'] = data.select('td')[1].get_text()
            data_dict['work_count'] = data.select('td')[2].get_text()
            data_dict['work_place'] = data.select('td')[3].get_text()
            data_dict['work_time'] = data.select('td')[4].get_text()

            # 將每條字典數(shù)據(jù)添加進列表
            self.item_list.append(data_dict)

        # 判斷是否是最后一頁损痰，條件：是否有noactive值
        # 先找到下一頁的標簽
        next_label = bs.select('#next')
        # 根據(jù)標簽獲取屬性class的值-返回結(jié)果為列表
        judge = next_label[0].get('class')

        return judge

    # 寫入文件
    def write_file(self):
        # 將列表轉(zhuǎn)換成字符串
        data_str = json.dumps(self.item_list)

        with open('04tencent_hr.json', 'w') as f:
            f.write(data_str)

    # 調(diào)度運行
    def run(self):
        while True:
            # 拼接參數(shù)
            params = {
                "keywords": "python",
                "tid": "0",
                "lid": "2156",
                "start": self.page,
            }

            # 發(fā)送請求
            data = self.send_request(self.base_url, params=params)

            # 解析數(shù)據(jù)
            judge = self.parse_data(data)

            self.page += 10
            print self.page

            # 如果到了最后一頁福侈，出現(xiàn)noactive，跳出循環(huán)
            if judge:
                break

        self.write_file()


if __name__ == '__main__':
    spider = tencent_hr()
    spider.run()