爬虫练习

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import urllib.request#这里必须要加request
import urllib.parse
import requests
import sys
#sys.Setdefaultencoding('utf-8')
import urllib
import json
import time
from bs4 import BeautifulSoup
#发起GET请求
# url = 'http://kaoshi.edu.sina.com.cn/college/scorelist?tab=batch&wl=1&local=2&batch=&syear=2013'
# response = urllib.request.urlopen(url=url)
# result = response.read().decode('utf-8')#解码后可以正常输出
# print(result)
#发起POST请求
url = "http://shuju.wdzj.com/plat-info-59.html"
data = urllib.parse.urlencode({'type1':'x','type2':0,'status':0}).encode('utf-8')
request = urllib.request.Request(url=url,data=data)
#opener = urllib.build_open(urllib.HTTPCookieProcessor()) #跟上述差不多,只是了一个data
response = urllib.request.urlopen(request)
result = response.read().decode('utf-8')
print(result)
result = result.replace('<html><head></head><body><pre style="word-wrap: break-word; white-space: pre-wrap;">', '')
result = result.replace('</pre></body></html>', '')
for key in json.loads(result,strict=False).keys():
    print(key)
#报错:json.decoder.JSONDecodeError: Expecting value: line 1 column 2 (char 1)
原文地址:https://www.cnblogs.com/lifengwu/p/9858998.html