python2使用bs4爬取腾讯社招过程解析

# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup as bs
import json
url = 'https://hr.tencent.com/position.php?'
params = {
  'start':'10'
}
headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
# 获取腾讯社招某个页面的页面源码
html = requests.get(url, params = params, headers = headers).text
# 创建soup对象，使用lxml解析器
soup = bs(html,'lxml')
# 选取类名为odd和even的tr标签
result1 = soup.select('tr[class="odd"]')
result2 = soup.select('tr[class="even"]')
# 列表拼接 l = [1,2] + [3,4]，则列表l为[1,2,3,4]
result = result1 + result2
# 把数据存放在列表里面，列表的每个元素都为一个字典
l = []
data = {}
for item in result:
  # 获取标签的文本内容
  job = item.find_all('a')[0].get_text().encode('utf-8')
  category = item.find_all('td')[1].get_text().encode('utf-8')
  number = item.find_all('td')[2].get_text().encode('utf-8')
  address = item.find_all('td')[3].get_text().encode('utf-8')
  public_time = item.find_all('td')[4].get_text().encode('utf-8')
  # 获取标签的属性值
  link = item.find_all('a')[0].attrs['href']
  fulllink = ('https://hr.tencent.com/' + link).encode('utf-8')
  data['job'] = job
  data['category'] = category
  data['number'] = number
  data['address'] = address
  data['public_time'] = public_time
  data['fulllink'] = fulllink
  l.append(data)
  # 原来中文写不到文件里面的报错原因，没把python列表序列化为json数组
  # with open('tencent.json','a') as f:
  #  f.write(str(data) + '\n')
# 方法1存储数据,上面字典的值不用先进行utf-8编码
# 把数据以json文件形式存储
# f = open('tencent.json','a')
# 把python列表序转化为json对象。本地操作常用的是load dump。网络操作常用的loads dumps，而loads常用来把json格式转化为python格式，dumps把python格式序列为json格式
# dictdata = json.dumps(l,ensure_ascii=False)
# 把json对象写入json文件
# f.write(dictdata.encode('utf-8'))
# f.close()

# 把数据存入tencent.json文件内
json.dump(l,open('tencent.json','a'),ensure_ascii=False)