爬蟲---學習筆記
爬蟲請求網站時要模擬瀏覽器,這就要用到User-Agent
#PC端UserAgent = {
"safari 5.1 – MAC":"User-Agent:Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"safari 5.1 – Windows":"User-Agent:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"IE 9.0":"User-Agent:Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0);",
"IE 8.0":"User-Agent:Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"IE 7.0":"User-Agent:Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"IE 6.0":"User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Firefox 4.0.1 – MAC":"User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Firefox 4.0.1 – Windows":"User-Agent:Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera 11.11 – MAC":"User-Agent:Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera 11.11 – Windows":"User-Agent:Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Chrome 17.0 – MAC":"User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Maxthon":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Tencent TT":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"The World 2.x":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"The World 3.x":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"sogou 1.x":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"360":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Avant":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"Green Browser":"User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)"
}
#phone
UserAgent = {
"iOS 4.33 – iPhone":"User-Agent:Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"iOS 4.33 – iPod Touch":"User-Agent:Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"iOS 4.33 – iPad":"User-Agent:Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Android N1":"User-Agent: Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Android QQ":"User-Agent: MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Android Opera ":"User-Agent: Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"Android Pad Moto Xoom":"User-Agent: Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"BlackBerry":"User-Agent: Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"WebOS HP Touchpad":"User-Agent: Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
"Nokia N97":"User-Agent: Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
"Windows Phone Mango":"User-Agent: Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UC":"User-Agent: UCWEB7.0.2.37/28/999",
"UC standard":"User-Agent: NOKIA5700/ UCWEB7.0.2.37/28/999",
"UCOpenwave":"User-Agent: Openwave/ UCWEB7.0.2.37/28/999",
"UC Opera":"User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999"
}
利用構建好的userAgents.py文件來充當爬蟲請求頭
#!/usr/bin/env python
#-*- coding: utf-8 -*-
import urllib2
import userAgents
'''userAgents.py是個自定義的模塊，位置處於當前目錄下 '''
class Urllib2ModifyHeader(object):
'''使用urllib2模塊修改header '''
def __init__(self):
# PC User-Agent
PCUA = userAgents.UserAgent.get('IE 9.0')
# Mobile User-Agent
MBUA = userAgents.UserAgent.get('UC standard')
#測試用的網站選擇的是有道翻譯
self.url = 'http://fanyi.youdao.com'
self.useUserAgent(PCUA,1)
self.useUserAgent(MBUA,2)
def useUserAgent(self,userAgent,name):
request = urllib2.Request(self.url)
request.add_header(userAgent.split(':')[0],userAgent.split(':')[1])
response = urllib2.urlopen(request)
fileName = str(name) + '.html'
with open(fileName,'a') as fp:
fp.write("%s\n\n" %userAgent)
fp.write(response.read())
if __name__ == '__main__':
umh = Urllib2ModifyHeader()
同一網站會給不同的瀏覽器返回不同的內容，使用網絡爬蟲時儘可能的添加一個固定的User-Agent