好久不更新博客了。。。
之前的博文都是通过urllib2进行http访问,接下来我要说一个利器啊!requests模块,无法用语言对他进行赞扬了,需要的,有兴趣的,可以去了解下,移步官方中文文档:
简直是不要太刁。。。
这篇博文呢,主要是将之前博文中用urllib2写的HttpClient类换成request。代码如下:
# coding=utf-8
from __future__ import unicode_literals
import requests
from io import StringIO
class HttpClient:
def __init__(self):
pass
__headers = {
'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:45.0) Gecko/20100101 Firefox/45.0',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Host':'www.xiami.com'
}
__proxies = {
# "http": "http://10.10.1.10:3128",
# "https": "http://10.10.1.10:1080",
}
def get(self, url, params=None, retries=3):
try:
req = requests.get(url, headers=self.__headers, timeout=30, params=params,
proxies=self.__proxies)
req.raise_for_status()
return req.text
except Exception,e:
print e
if retries > 0:
return self.get(url, params, retries - 1)
else:
print "Get Failed", url
return ''
def post(self, url, data=None, retires=3):
try:
req = requests.post(url, headers=self.__headers, timeout=30, data=data,
proxies=self.__proxies)
req.raise_for_status()
return req.text
except Exception,e:
print e
if retires > 0:
return self.post(url,data,retires - 1)
else:
print "Post Failed", url
return ''
def download(self, url, file_name, params=None, cookies=None):
try:
req = requests.get(url, headers=self.__headers, params=params,
proxies=self.__proxies)
output = open(file_name, 'wb')
output.write(req.content)
output.close()
except Exception,e:
print 'error',e
def get_cookies(self, url, key, params=None):
try:
req = requests.get(url, headers=self.__headers, timeout=30, params=params,
proxies=self.__proxies)
req.raise_for_status()
return req.cookies.get(key,'')
except Exception,e:
return ''
def get_headers(self, url, key, params=None):
try:
req = requests.get(url, headers=self.__headers, timeout=30, params=params,
proxies=self.__proxies)
req.raise_for_status()
return req.headers.get(key)
except Exception,e:
return ''
记录一下,后面会时常更新博文的。