思路分析

特别说明

本文以Java工作岗位信息为例进行说明，如果想爬取其他岗位的信息，更改URL请求中的关键字即可。方法仅供交流学习，不要用来做违法的事情。
在这里插入图片描述

1、获取PostId列表

由于网页中每一个职位都有一个PostId，而爬取职位的详情信息时，需要用到PostId来构造请求的URL，因此，我先将职位的PostId存放到列表中，为下一步爬取职位的详情信息做准备。

def get_url():
    # 爬取的页数，这里爬取前10页
    endIndex = 10
    postId = []
    for pageIndex in range(1, endIndex+1):
        query['timestamp'] = int(time.time())
        query['pageIndex'] = pageIndex
        url = raw_url.format(query['timestamp'], query['keyword'], query['pageIndex'], query['pageSize'],
                             query['language'], query['area'])
        try:
            r = requests.get(url, headers=headers)
        except :
            print("请求失败！")
            continue
        data_list = json.loads(r.text)['Data']['Posts']
        for item in data_list:
            postId.append(item['PostId'])
            print(item['PostId'])
    return postId

2、爬取详情页面

利用上一步得到的PostId列表即可构造URL发送请求，这里可以用Python的time模块来处理时间戳的问题，然后，再将爬到信息以列表的形式返回，方便后面进行数据存储。

def get_detail(post_id):
    data_list = []
    for it in post_id:
        url = post_url % (int(time.time()), it)
        try:
            response = requests.get(url, headers)
        except :
            print("请求失败！")
            continue
        if response.status_code == 200:
            data = json.loads(response.text)['Data']
            data_list += [data]
            print(data)
    return data_list

3、保存数据

将数据保存成CSV文件即可

def save_to_file(data_list):
    df = pd.DataFrame(data_list)
    df.to_csv('./result/tencent.csv', index=False, encoding='utf_8_sig')

完整代码

# ！/usr/bin/env python
# —*— coding: utf-8 —*—
# @Time:    2020/2/2 14:36
# @Author:  Martin
# @File:    tencent_hr.py
# @Software:PyCharm
import requests
import time
import json
from lxml import etree
import pandas as pd

# 请求头部信息
headers = {
    'referer': 'https://careers.tencent.com/search.html?keyword=Java',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
}
query = {
    'timestamp': '',
    'countryId': '',
    'cityId': '',
    'bgIds': '',
    'productId': '',
    'categoryId': '',
    'parentCategoryId': '',
    'attrId': '',
    'keyword': 'Java',
    'pageIndex': '',
    'pageSize': '10',
    'language': 'zh-cn',
    'area': 'cn'
}
raw_url = 'https://careers.tencent.com/tencentcareer/api/post/Query?timestamp={}&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword={}&pageIndex={}&pageSize={}&language={}&area={}'
post_url = 'https://careers.tencent.com/tencentcareer/api/post/ByPostId?timestamp=%d&postId=%s&language=zh-cn'


def get_url():
    # 爬取的页数，这里爬取前10页
    endIndex = 10
    postId = []
    for pageIndex in range(1, endIndex+1):
        query['timestamp'] = int(time.time())
        query['pageIndex'] = pageIndex
        url = raw_url.format(query['timestamp'], query['keyword'], query['pageIndex'], query['pageSize'],
                             query['language'], query['area'])
        try:
            r = requests.get(url, headers=headers)
        except :
            print("请求失败！")
            continue
        data_list = json.loads(r.text)['Data']['Posts']
        for item in data_list:
            postId.append(item['PostId'])
            print(item['PostId'])
    return postId


def get_detail(post_id):
    data_list = []
    for it in post_id:
        url = post_url % (int(time.time()), it)
        try:
            response = requests.get(url, headers)
        except :
            print("请求失败！")
            continue
        if response.status_code == 200:
            data = json.loads(response.text)['Data']
            data_list += [data]
            print(data)
    return data_list


def save_to_file(data_list):
    df = pd.DataFrame(data_list)
    df.to_csv('./result/tencent.csv', index=False, encoding='utf_8_sig')


def spider():
    postId = get_url()
    save_to_file(get_detail(postId))


if __name__ == '__main__':
    spider()