初学爬虫-腾讯招聘爬虫

import time
import datetime
import random
import requests

获取一个时间戳

def get_timeStamp():
    times = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    timeArray = time.strptime(times, "%Y-%m-%d %H:%M:%S")
    timeStamp = str(int(time.mktime(timeArray)))
    random_tamp = str(random.randint(100, 1000))
    timestamp = timeStamp + random_tamp
    return timestamp

爬取5页的数据

for i in range(1,5):
	#调用上面的函数生成时间戳参数
    timestamp = get_timeStamp()
    pageIndex = str(i) #获取页码
    url = 'https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=' + timestamp + '&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword=&pageIndex=' + pageIndex + '&pageSize=10&language=zh-cn&area=cn'
    content = requests.get(url).json()
    purl_lists = content['Data']['Posts']
    for i in purl_lists:
        post_id = i['PostId']
        content_url = 'https://careers.tencent.com/tencentcareer/api/post/ByPostId?timestamp='+ timestamp+ '&postId='+post_id+'&language=zh-cn'

        content = requests.get(content_url).json()['Data']
        print(content)