Python招聘网站数据分析源码

以下是一个使用 Python 进行爬虫和数据分析的招聘网站源码示例：

import requests
from bs4 import BeautifulSoup
import pandas as pd

# 定义爬虫函数
def get_job_list(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    jobs = soup.find_all('div', {'class': 'job-primary'})
    job_list = []
    for job in jobs:
        try:
            title = job.find('div', {'class': 'job-title'}).text.strip()
        except:
            title = ''
        try:
            salary = job.find('span', {'class': 'red'}).text.strip()
        except:
            salary = ''
        try:
            company = job.find('div', {'class': 'company-text'}).a.text.strip()
        except:
            company = ''
        try:
            location = job.find('div', {'class': 'job-address'}).text.strip()
        except:
            location = ''
        job_list.append([title, salary, company, location])
    return job_list

# 爬取数据
url = 'https://www.zhipin.com/c100010000/?query=Python&page={}'
job_list = []
for i in range(1, 11):
    url_page = url.format(i)
    job_list += get_job_list(url_page)

# 转换数据为 DataFrame 格式
df = pd.DataFrame(job_list, columns=['Title', 'Salary', 'Company', 'Location'])

# 数据清洗和处理
df.drop_duplicates(inplace=True)
df.reset_index(drop=True, inplace=True)
df['Salary_min'] = df.Salary.apply(lambda x: x.split('-')[0] if '-' in x else x)
df['Salary_max'] = df.Salary.apply(lambda x: x.split('-')[1] if '-' in x else x)
df['Salary_min'] = df.Salary_min.apply(lambda x: x.replace('K', '000').replace('以上', ''))
df['Salary_max'] = df.Salary_max.apply(lambda x: x.replace('K', '000').replace('以上', ''))
df['Salary_min'] = pd.to_numeric(df.Salary_min)
df['Salary_max'] = pd.to_numeric(df.Salary_max)
df['Salary_avg'] = (df.Salary_min + df.Salary_max) / 2
df['Location'] = df.Location.apply(lambda x: x.split('·')[0])

# 数据分析
location_group = df.groupby('Location')['Title'].count().reset_index().sort_values(by='Title', ascending=False)
salary_group = df.groupby('Location')['Salary_avg'].mean().reset_index().sort_values(by='Salary_avg', ascending=False)

# 结果输出
print('地区招聘数量排名：\n', location_group.head(10))
print('\n地区薪资水平排名：\n', salary_group.head(10))

这个示例使用 `requests` 和 `BeautifulSoup` 库进行网页爬取和解析，然后使用 `pandas` 库将数据转换为 DataFrame 格式进行清洗和处理，最后使用 DataFrame 的 groupby() 函数进行数据分析。输出结果为地区招聘数量排名和地区薪资水平排名。