Pyspider 中采用了 tornado 庫來做 http 請求，在請求過程中可以添加各種參數，例如請求鏈接超時時間，請求傳輸數據超時時間，請求頭等等，但是根據pyspider的原始框架，給爬蟲添加參數只能通過 crawl_config這個Python字典來完成(如下所示)，框架代碼將這個字典中的參數轉換成 task 數據，進行http請求。這個參數的缺點是不方便給每一次請求做隨機請求頭。
crawl_config = {"user_agent": "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36","timeout": 120,"connect_timeout": 60,"retries": 5,"fetch_type": 'js',"auto_recrawl": True,}這里寫出給爬蟲添加隨機請求頭的方法：
1、編寫腳本，將腳本放置在 pyspider 的 libs 文件夾下，命名為 header_switch.py
#!/usr/bin/env python# -*- coding:utf-8 -*-# Created on 2017-10-18 11:52:26import randomimport timeclass HeadersSelector(object): """ Header 中缺少幾個字段 Host 和 Cookie """ headers_1 = { "Proxy-Connection": "keep-alive", "Pragma": "no-cache", "Cache-Control": "no-cache", "User-Agent": "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36", "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", "DNT": "1", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.4", "Referer": "https://www.baidu.com/s?wd=%BC%96%E7%A0%81&rsv_spt=1&rsv_iqid=0x9fcbc99a0000b5d7&issp=1&f=8&rsv_bp=1&rsv_idx=2&ie=utf-8&rqlang=cn&tn=baiduhome_pg&rsv_enter=0&oq=If-None-Match&inputT=7282&rsv_t", "Accept-Charset": "gb2312,gbk;q=0.7,utf-8;q=0.7,*;q=0.7", } # 網上找的瀏覽器 headers_2 = { "Proxy-Connection": "keep-alive", "Pragma": "no-cache", "Cache-Control": "no-cache", "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0", "Accept": "image/gif,image/x-xbitmap,image/jpeg,application/x-shockwave-flash,application/vnd.ms-excel,application/vnd.ms-powerpoint,application/msword,*/*", "DNT": "1", "Referer": "https://www.baidu.com/link?url=c-FMHf06-ZPhoRM4tWduhraKXhnSm_RzjXZ-ZTFnPAvZN", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.4", } # window 7 系統瀏覽器 headers_3 = { "Proxy-Connection": "keep-alive", "Pragma": "no-cache", "Cache-Control": "no-cache", "User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0", "Accept": "image/x-xbitmap,image/jpeg,application/x-shockwave-flash,application/vnd.ms-excel,application/vnd.ms-powerpoint,application/msword,*/*", "DNT": "1", "Referer": "https://www.baidu.com/s?wd=http%B4%20Pragma&rsf=1&rsp=4&f=1&oq=Pragma&tn=baiduhome_pg&ie=utf-8&usm=3&rsv_idx=2&rsv_pq=e9bd5e5000010", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.7,en;q=0.6", } # Linux 系統 firefox 瀏覽器 headers_4 = { "Proxy-Connection": "keep-alive", "Pragma": "no-cache", "Cache-Control": "no-cache", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:55.0) Gecko/20100101 Firefox/55.0", "Accept": "*/*", "DNT": "1", "Referer": "https://www.baidu.com/link?url=c-FMHf06-ZPhoRM4tWduhraKXhnSm_RzjXZ-ZTFnP", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.7,en;q=0.6", } # Win10 系統 firefox 瀏覽器 headers_5 = { "Connection": "keep-alive", "Pragma": "no-cache", "Cache-Control": "no-cache", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64;) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36 Edge/15.15063", "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", "Referer": "https://www.baidu.com/link?url=c-FMHf06-ZPhoRM4tWduhraKXhnSm_RzjXZ-", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.7,en;q=0.6", "Accept-Charset": "gb2312,gbk;q=0.7,utf-8;q=0.7,*;q=0.7", } # Win10 系統 Chrome 瀏覽器 headers_6 = { "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", "Accept-Encoding": "gzip, deflate, sdch", "Accept-Language": "zh-CN,zh;q=0.8", "Pragma": "no-cache", "Cache-Control": "no-cache", "Connection": "keep-alive", "DNT": "1", "Referer": "https://www.baidu.com/s?wd=If-None-Match&rsv_spt=1&rsv_iqid=0x9fcbc99a0000b5d7&issp=1&f=8&rsv_bp=1&rsv_idx=2&ie=utf-8&rq", "Accept-Charset": "gb2312,gbk;q=0.7,utf-8;q=0.7,*;q=0.7", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0", } # win10 系統瀏覽器 def __init__(self): pass def select_header(self): n = random.randint(1, 6) switch={ 1: self.headers_1 2: self.headers_2 3: self.headers_3 4: self.headers_4 5: self.headers_5 6: self.headers_6 } headers = switch[n] return headers其中，我只寫了6個請求頭，如果爬蟲的量非常大，完全可以寫更多的請求頭，甚至上百個，然后將 random的隨機范圍擴大，進行選擇。
2、在pyspider 腳本中編寫如下代碼：
#!/usr/bin/env python# -*- encoding: utf-8 -*-# Created on 2017-08-18 11:52:26from pyspider.libs.base_handler import *from pyspider.addings.headers_switch import HeadersSelectorimport sysdefaultencoding = 'utf-8'if sys.getdefaultencoding() != defaultencoding: reload(sys) sys.setdefaultencoding(defaultencoding)class Handler(BaseHandler): crawl_config = { "user_agent": "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36", "timeout": 120, "connect_timeout": 60, "retries": 5, "fetch_type": 'js', "auto_recrawl": True, } @every(minutes=24 * 60) def on_start(self): header_slt = HeadersSelector() header = header_slt.select_header() # 獲取一個新的 header # header["X-Requested-With"] = "XMLHttpRequest" orig_href = 'http://sww.bjxch.gov.cn/gggs.html' self.crawl(orig_href, callback=self.index_page, headers=header) # 請求頭必須寫在 crawl 里，cookies 從 response.cookies 中找 @config(age=24 * 60 * 60) def index_page(self, response): header_slt = HeadersSelector() header = header_slt.select_header() # 獲取一個新的 header # header["X-Requested-With"] = "XMLHttpRequest" if response.cookies: header["Cookies"] = response.cookies其中最重要的就是在每個回調函數 on_start，index_page 等等 當中，每次調用時，都會實例化一個 header 選擇器，給每一次請求添加不一樣的 header。要注意添加的如下代碼：
header_slt = HeadersSelector() header = header_slt.select_header() # 獲取一個新的 header # header["X-Requested-With"] = "XMLHttpRequest" header["Host"] = "www.baidu.com" if response.cookies: header["Cookies"] = response.cookies
當使用 XHR 發送 AJAX 請求時會帶上 Header，常被用來判斷是不是 Ajax 請求， headers 要添加 {‘X-Requested-With': ‘XMLHttpRequest'} 才能抓取到內容。
確定了 url 也就確定了請求頭中的 Host，需要按需添加，urlparse包里給出了根據 url解析出 host的方法函數，直接調用netloc即可。
如果響應中有 cookie，就需要將 cookie 添加到請求頭中。
如果還有別的偽裝需求，自行添加。
如此即可實現隨機請求頭，完。
以上這篇Pyspider中給爬蟲偽造隨機請求頭的實例就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支持VEVB武林網。
新聞熱點
疑難解答
