Python爬虫案例八：抓取597招聘网信息并用xlutils进行excel数据的保存

excel保存数据的三种方式：

1、pandas保存excel数据，后缀名为xlsx;

举例：
import pandas as pd

dic = {
    '姓名': ['张三', '李四', '王五', '赵六'],
    '年龄': ['18', '19', '20', '21'],
    '住址': ['广州', '青岛', '南京', '重庆']
}
dic_file = pd.DataFrame(dic)
dic_file.to_excel('2.xlsx', index=False)
2、openpyxl保存excel数据，后缀名为xlsx；
---------A、覆盖数据-----------
from openpyxl import Workbook  
# 1、创建工作簿
wb = Workbook()

# 确定某一张表  
sheet = wb.active

# 2、数据读写
info_list = [
    ['姓名', '年龄', '性别'],
    ['张三', '19', '男'],
    ['李四', '20', '女'],
    ['王五', '21', '女']
]
for info in info_list:
    sheet.append(info)

sheet.append(['tom', '12', '女'])

# 3、保存
wb.save('2.xlsx')

-----------B、追加数据---------
from openpyxl import load_workbook

wb = load_workbook('2.xlsx')

sheet.append(['王五', '21', '女'])

sheet.save('2.xlsx')
3、xlutils保存excel数据，后缀名为xls【使用模版代码】。xlutils是一个库，它是一个成品案

使用步骤：

（1）构造一个字典，如 data = { '表名': ['张三', '18', '本科'] }

（2）复制成品代码

（3）调用保存函数

（4）修改某些内容【表头文件名xls 表名=键】

（5）复制导包

测试链接：https://fz.597.com/zhaopin/?page=1

代码：



import requests
from lxml import etree
import os, xlwt, xlrd
from xlutils.copy import copy

class OneSpider(object):
    def __init__(self):
        self.no = 1
        self.city = '福州'
        self.is_text = True
        self.keyword = '司机'
        self.start_url = 'https://fz.597.com/zhaopin/c3/?'
        self.headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36'
        }

    def request_url(self):
        while self.is_text:
            # 发送请求
            params = {
                'q': self.keyword,
                'page': f'{self.no}'
            }
            response = requests.get(self.start_url, headers=self.headers, params=params).text
            self.parse_response(response)
            self.no += 1
        print('------爬虫结束--------')

    def parse_response(self, response):
        A = etree.HTML(response)
        self.is_text = A.xpath('//div[@class="page"]/a[last()]/text()')
        # print(self.is_text)
        self.is_text = ''.join(self.is_text)
        self.is_text = True if self.is_text == '尾页' else False
        # -----解析正文----------
        div_list = A.xpath('//div[@class="firm_box"]/div[@class="firm-item"]')
        for div in div_list:
            zw = div.xpath('.//ul[@class="firm-list2"]/li[1]/a//text()')[0]
            gs = div.xpath('.//ul[@class="firm-list2"]/li[2]/a/text()')[0]
            info_id = div.xpath('.//ul[@class="firm-list2"]/li[1]/a/@href')[0].split('/job-')[-1].split('.html')[0]
            self.request_info_url(zw, gs, info_id)

    def request_info_url(self, zw, gs, info_id):
        # 请求详情页
        info_url = 'https://fz.597.com/job-{}.html'.format(info_id)
        response = requests.get(info_url, headers=self.headers).text
        self.parse_info_response(response, zw, gs)

    def parse_info_response(self, response, zw, gs):
        # 解析详情页
        A = etree.HTML(response)
        nr = A.xpath('.//div[@class="newTytit"]//text()')
        nr = ''.join([i.strip() for i in nr])
        sj_ts = A.xpath('//div[@class="newJobDtl "]/p[5]//text()')
        sj_ts = ''.join([i.strip() for i in sj_ts])
        # 对sj做细致的处理
        sj_ts = sj_ts.split('时间：')[-1]
        if '|' in sj_ts and '/' in sj_ts:
            sj = sj_ts.split('|')[0]
            ts = sj_ts.split('|')[1]
        else:
            if '|' in sj_ts:
                sj = sj_ts.split('|')[0]
                ts = '--'
            elif '/' in sj_ts:
                sj = '--'
                ts = sj_ts
            else:
                sj = '--'
                ts = '--'

        data = {
            '信息': [zw, gs, sj, ts, nr]
        }
        self.save_data(data, zw)
        self.no += 1

    def save_data(self, data, zw):
        '''
            保存excel模板代码
        '''
        if not os.path.exists(f'{self.city}_{self.keyword}招聘信息.xls'):
            # 1、创建 Excel 文件
            wb = xlwt.Workbook(encoding='utf-8')
            # 2、创建新的 Sheet 表
            sheet = wb.add_sheet('信息', cell_overwrite_ok=True)
            # 3、设置 Borders边框样式
            borders = xlwt.Borders()
            borders.left = xlwt.Borders.THIN
            borders.right = xlwt.Borders.THIN
            borders.top = xlwt.Borders.THIN
            borders.bottom = xlwt.Borders.THIN
            borders.left_colour = 0x40
            borders.right_colour = 0x40
            borders.top_colour = 0x40
            borders.bottom_colour = 0x40
            style = xlwt.XFStyle()
            style.borders = borders
            align = xlwt.Alignment()
            align.horz = 0x02
            align.vert = 0x01
            style.alignment = align
            header = ('职位名称', '公司名字', '时间', '天数', '内容')
            for i in range(0, len(header)):
                sheet.col(i).width = 2560 * 3
                sheet.write(0, i, header[i], style)
                wb.save(f'{self.city}_{self.keyword}招聘信息.xls')
        if os.path.exists(f'{self.city}_{self.keyword}招聘信息.xls'):
            wb = xlrd.open_workbook(f'{self.city}_{self.keyword}招聘信息.xls')
            sheets = wb.sheet_names()
            for i in range(len(sheets)):
                for name in data.keys():
                    worksheet = wb.sheet_by_name(sheets[i])
                    if worksheet.name == name:
                        rows_old = worksheet.nrows
                        new_workbook = copy(wb)
                        new_worksheet = new_workbook.get_sheet(i)
                        for num in range(0, len(data[name])):
                            new_worksheet.write(rows_old, num, data[name][num])
                        new_workbook.save(f'{self.city}_{self.keyword}招聘信息.xls')
        print(r'***正在保存第{}条信息：{}'.format(self.no, zw))

    def main(self):
        self.request_url()

if __name__ == '__main__':
    one = OneSpider()
    one.main()

运行效果：