# -*- coding: utf-8 -*-
"""
Created on Fri Apr 7 13:18:02 2017
@author: jcj
"""
#from urllib import urlopen
import urllib2
#import requests
from bs4 import BeautifulSoup
class JobScrapy():
def __init__(self):
'''初始化函数:初始化内容包括headers'''
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
self.myheaders = { 'User-Agent' : user_agent }
self.myhomeUrl = []
def setUrl(self,strUrl):#该方法用来设置homeUrl
'''设置读取的homepage'''
self.myhomeUrl = strUrl
def load_homePage(self):#通过homeUrl访问网址,并返回访问得到的xml文件
'''加载homepage'''
req = urllib2.Request(url = self.myhomeUrl, data = None, headers = self.myheaders)
home_request = urllib2.urlopen(req)
home_html = home_request.read()
return home_html
def load_cityPage(self,strCity):
'''加载citypage'''
cityUrl = self.myhomeUrl+'/'+strCity+'/'
req = urllib2.Request(url = cityUrl,data = None, headers = self.myheaders)
city_request = urllib2.urlopen(req)
city_html = city_request.read()
return city_html
# def down_jobinfo(self,path):
def main():
site = 'http://www.yingjiesheng.com'
JS = JobScrapy()
JS.setUrl(site)
home_html = JS.load_homePage()
city_html = JS.load_cityPage('beijing')
city_soup = BeautifulSoup(city_html,from_encoding='GBK')
print city_soup
if __name__ == '__main__':
main()
Python代码读取网页时发生错误,请问我的代码该怎么改?
- 写回答
- 好问题 0 提建议
- 追加酬金
- 关注问题
- 邀请回答
-
2条回答 默认 最新
- vip_ing 2017-04-10 04:02关注
city_soup = BeautifulSoup(city_html,from_encoding='GBK') 改为
city_soup = BeautifulSoup(city_html, 'lxml', from_encoding='GBK')本回答被题主选为最佳回答 , 对您是否有帮助呢?解决 无用评论 打赏 举报
悬赏问题
- ¥15 HFSS 中的 H 场图与 MATLAB 中绘制的 B1 场 部分对应不上
- ¥15 如何在scanpy上做差异基因和通路富集?
- ¥20 关于#硬件工程#的问题,请各位专家解答!
- ¥15 关于#matlab#的问题:期望的系统闭环传递函数为G(s)=wn^2/s^2+2¢wn+wn^2阻尼系数¢=0.707,使系统具有较小的超调量
- ¥15 FLUENT如何实现在堆积颗粒的上表面加载高斯热源
- ¥30 截图中的mathematics程序转换成matlab
- ¥15 动力学代码报错,维度不匹配
- ¥15 Power query添加列问题
- ¥50 Kubernetes&Fission&Eleasticsearch
- ¥15 報錯:Person is not mapped,如何解決?