import urllib.request
from bs4 import BeautifulSoup
import time
import pymysql
def headers_request(url):
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36'}
request=urllib.request.Request(url,headers=headers)
return request解析内容
def parse_content(content, db):
# 生成soup对象
soup = BeautifulSoup(content,'lxml')
# 先找包含所有工作的div
odivbox = soup.find('div',id='resultList')
# 首先找到包含所有工作的div
odiv_list = odivbox.find_all('div',class_='el')[1:]
# print(len(odiv_list))
for odiv in odiv_list:
# 职位名称
jobname = odiv.select('.t1 > span > a')[0]['title']
# 公司名称
company = odiv.select('.t2 > a')[0]['title']
# 工作地点
area = odiv.select('.t3')[0].string
# 职位月薪
salary = odiv.select('.t4')[0].string
# 发布时间
publish_time = odiv.select('.t5')[0].string
# print(salary, publish_time)
# 保存到字典中
item = {
'职位名称':jobname,
'公司名称':company,
'工作地点':area,
'职位月薪':salary,
'发布时间':publish_time
}
# 保存到文件中
# string = str(item) + '\n'
# fp.write(string)
# 保存到mysql中
save_to_mysql(db,item)def save_to_mysql(db,item):
# 获取游标
cur = db.cursor()
# 执行sql语句
sql = """insert into work(jobname,company,area,salary,publish_time) values('%s','%s','%s','%s','%s')""" % (item['职位名称'], item['公司名称'], item['工作地点'], item['职位月薪'], item['发布时间'])
# print(sql)
try:
cur.execute(sql)
#提交
db.commit()
except Exception as e:
# print(e)
#错误回滚
db.rollback()def main():
# fp = open('work.txt','w',encoding='utf8')
# 链接数据库
db = pymysql.connect(host="xxxx",user="xxxx",password="xxxxxx",db="xx",port=xxxx,charset='utf8')
# 用户输入要搜索工作关键字
keyword = input('请输入要搜索的关键字-')
# 用户输入要爬取的起始和结束页码
start_page = int(input('请输入要爬取的起始页码-'))
end_page = int(input('请输入要爬取的结束页码-'))
# 要拼接的起始url
url = 'https://search.51job.com/list/010000,000000,0000,00,9,99,{},2,{}.html'
# 写循环，每一页开始挨着爬取
for page in range(start_page,end_page + 1):
print('[金融期货](https://www.gendan5.com/futures/ff.html)正在爬取第%s页......' % page)
# 拼接url
url_page = url.format(keyword,page)
# print(url_page)
# 构建请求对象
request = headers_request(url_page)
# 发送请求，得到响应
content = urllib.request.urlopen(request).read().decode('gbk')
# 解析内容
parse_content(content,db)
print('结束爬取第%s页' % page)
time.sleep(2)
# fp.close()
db.close()if name == '__main__':
main()