2024年Python最全Python爬取Boss直聘,帮你获取全国各类职业薪酬榜(1)

代码


import requests

from bs4 import BeautifulSoup

import csv

import random

import time

import argparse

from pyecharts.charts import Line

import pandas as pd

class BossCrawler:

def init(self, query):

self.query = query

self.filename = ‘boss_info_%s.csv’ % self.query

self.city_code_list = self.get_city()

self.boss_info_list = []

self.csv_header = [“city”, “profession”, “salary”, “company”]

@staticmethod

def getheaders():

user_list = [

“Opera/9.80 (X11; Linux i686; Ubuntu/14.10) Presto/2.12.388 Version/12.16”,

“Opera/9.80 (Windows NT 6.0) Presto/2.12.388 Version/12.14”,

“Mozilla/5.0 (Windows NT 6.0; rv:2.0) Gecko/20100101 Firefox/4.0 Opera 12.14”,

“Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0) Opera 12.14”,

“Opera/12.80 (Windows NT 5.1; U; en) Presto/2.10.289 Version/12.02”,

“Opera/9.80 (Windows NT 6.1; U; es-ES) Presto/2.9.181 Version/12.00”,

“Opera/9.80 (Windows NT 5.1; U; zh-sg) Presto/2.9.181 Version/12.00”,

“Opera/12.0(Windows NT 5.2;U;en)Presto/22.9.168 Version/12.00”,

“Opera/12.0(Windows NT 5.1;U;en)Presto/22.9.168 Version/12.00”,

“Mozilla/5.0 (Windows NT 5.1) Gecko/20100101 Firefox/14.0 Opera/12.0”,

“Opera/9.80 (Windows NT 6.1; WOW64; U; pt) Presto/2.10.229 Version/11.62”,

“Opera/9.80 (Windows NT 6.0; U; pl) Presto/2.10.229 Version/11.62”,

“Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52”,

“Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; de) Presto/2.9.168 Version/11.52”,

“Opera/9.80 (Windows NT 5.1; U; en) Presto/2.9.168 Version/11.51”,

“Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; de) Opera 11.51”,

“Opera/9.80 (X11; Linux x86_64;

你可能感兴趣的:(程序员,python,开发语言)