# -*- 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'
}
# 獲取騰訊社招某個頁面的頁面源碼
html = requests.get(url, params = params, headers = headers).text
# 創(chuàng)建soup對象，使用lxml解析器
soup = bs(html,'lxml')
# 選取類名為odd和even的tr標簽
result1 = soup.select('tr[class="odd"]')
result2 = soup.select('tr[class="even"]')
# 列表拼接 l = [1,2] + [3,4]，則列表l為[1,2,3,4]
result = result1 + result2
# 把數(shù)據(jù)存放在列表里面，列表的每個元素都為一個字典
l = []
data = {}
for item in result:
  # 獲取標簽的文本內(nèi)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')
  # 獲取標簽的屬性值
  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)
  # 原來中文寫不到文件里面的報錯原因，沒把python列表序列化為json數(shù)組
  # with open('tencent.json','a') as f:
  #  f.write(str(data) + '\n')
# 方法1存儲數(shù)據(jù),上面字典的值不用先進行utf-8編碼
# 把數(shù)據(jù)以json文件形式存儲
# f = open('tencent.json','a')
# 把python列表序轉(zhuǎn)化為json對象。本地操作常用的是load dump。網(wǎng)絡操作常用的loads dumps，而loads常用來把json格式轉(zhuǎn)化為python格式，dumps把python格式序列為json格式
# dictdata = json.dumps(l,ensure_ascii=False)
# 把json對象寫入json文件
# f.write(dictdata.encode('utf-8'))
# f.close()

# 把數(shù)據(jù)存入tencent.json文件內(nèi)
json.dump(l,open('tencent.json','a'),ensure_ascii=False)