项目：招聘网站信息（获取数据+数据分析+数据可视化）.pdfVIP

项⽬：招聘⽹站信息（获取数据+数据分析+数据可视化） 在本次项⽬中，使⽤到的第三⽅库如下: import requests import time import random import json import pandas import matplotlib.pyplot import csv import numpy import WordCloud import jieba 项⽬实现流程如下： ⼀、利⽤requests库模块进⾏对招聘⽹站信息的爬取 代码如下： import requests import time import random import json import pandas as pd import matplotlib.pyplot as plt page_num_max = 3 class Recruitment_info(): def __init__(self): self.zhilian_url = /api/sou/positionlist def get_page(self,search_content,page_num): url = self.zhilian_url headers = {user-agent:self.get_ua()} data = self.get_data(search_content,page_num) html = requests.post(url=url,headers=headers,data=data).text return html def get_data(self,search_content,page_num): t = 0123456789abide d = XXXXXXXX-XXXX-4XXX-XXXX-XXXXXXXXXXXX for i in range(35): t_rd = random.choice(t) d = d.replace(X, t_rd, 1) data = { S_SOU_FULL_INDEX: search_content, S_SOU_WORK_CITY: 489, at: , channel: baidupcpz, d: d, eventScenario: msiteSeoSearchSouList, pageIndex: page_num, pageSize: 20, platform: 7, platform: 7, rt: , utmsource: baidupcpz, } return json.dumps(data) def get_ua(self): Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) GeckoFirefox/6.0, Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Mobile Safari/537.36] return random.choice(ua_list) def Data_cleaning(self,html): resurt = json.loads(html) resurt = resurt[data][list] data_list = [] for per_info in resurt: data = { cityId : per_inf