scrapy实战:伪造headers的多种实现

新建爬虫

为了分析我们伪造headers是否成功,我们先新建一个爬虫,目标可以随便选,我这里直接借用下个论题要用的爬虫。

#进入虚拟环境
cd /data/code/python/venv/venv_Scrapy/tutorial
# 新建爬虫
../bin/python3 ../bin/scrapy genspider -t basic ip138 www.ip138.com

ip138.py

修改 ip138.py 功能很简单只需要打印出全部的headers meta cookies,这里我们先只关注request headers

# -*- coding: utf-8 -*-
import scrapy

class Ip138Spider(scrapy.Spider):
    name = 'ip138'
    allowed_domains = ['www.ip138.com','2018.ip138.com']
    start_urls = ['http://2018.ip138.com/ic.asp']

    def parse(self, response):
        print("*" * 40)
        print("response text: %s" % response.text)
        print("response headers: %s" % response.headers)
        print("response meta: %s" % response.meta)
        print("request headers: %s" % response.request.headers)
        print("request cookies: %s" % response.request.cookies)
        print("request meta: %s" % response.request.meta)

默认headers

运行爬虫

../bin/python3 ../bin/scrapy crawl ip138

结果如下:
默认headers

很明显这种默认的request.headers很容易被封,我们需要伪装自己的headers

默认User-Agent

我们先尝试修改 默认的User-Agent

settins.py

 # Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'tutorial (+http://www.yourdomain.com)'
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1'

运行结果如下
user-agent

默认HEADERS

settins.py

#Override the default request headers:
DEFAULT_REQUEST_HEADERS = {
  # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  # 'Accept-Language': 'en',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.89 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.5,en;q=0.3",
    "Accept-Encoding": "gzip, deflate",
    'Content-Length': '0',
    "Connection": "keep-alive"
}

运行结果
headers

custom_settings

除了可以在 settins.py 中设置,我们也可以为爬虫单独设置headers,例如

    custom_settings = {
        'DEFAULT_REQUEST_HEADERS' : {
            'User-Agent': 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
            "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.5,en;q=0.3",
            "Accept-Encoding": "gzip, deflate",
            'Content-Length': '0',
            "Connection": "keep-alive"
        }
    }

运行结果
custome_setting

headers=headers

# -*- coding: utf-8 -*-
import scrapy


class Ip138Spider(scrapy.Spider):
    name = 'ip138'
    allowed_domains = ['www.ip138.com','2018.ip138.com']
    start_urls = ['http://2018.ip138.com/ic.asp']
    
    headers = {
        'User-Agent': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.5,en;q=0.3",
        "Accept-Encoding": "gzip, deflate",
        'Content-Length': '0',
        "Connection": "keep-alive"
    }

    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.Request(url, headers=self.headers ,callback=self.parse)

    def parse(self, response):
        print("*" * 40)
        print("response text: %s" % response.text)
        print("response headers: %s" % response.headers)
        print("response meta: %s" % response.meta)
        print("request headers: %s" % response.request.headers)
        print("request cookies: %s" % response.request.cookies)
        print("request meta: %s" % response.request.meta)

结果如下
headers=

Middleware中间件设置

我们使用startproject 创建项目的时候系统已经自动为我们创建了 middlewares.py 中间件py

我们可以在DownloaderMiddleware中间件中设置headers

middlewares.py

class TutorialDownloaderMiddleware(object):
    def process_request(self, request, spider):
    	request.headers.setdefault('User-Agent', 'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5')

当然我们也可以设置完整的headers

from scrapy.http.headers import Headers
headers = {
    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.5,en;q=0.3",
    "Accept-Encoding": "gzip, deflate",
    'Content-Length': '0',
    "Connection": "keep-alive"
}
class TutorialDownloaderMiddleware(object):
    def process_request(self, request, spider):
        request.headers = Headers(headers)

settings.py

启动中间件

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
    'tutorial.middlewares.TutorialDownloaderMiddleware': 1,
}

简单动态 User-Agent

在settings文件中添加一些UserAgent

settings.py

USER_AGENT_LIST=[
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
    "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "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)",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
]

middlewares.py

from tutorial.settings import USER_AGENT_LIST
class TutorialDownloaderMiddleware(object):
    def process_request(self, request, spider):
    	request.headers.setdefault('User-Agent', random.choice(USER_AGENT_LIST))

fake-useragent 切换User-Agent

安装

../bin/pip3 install fake-useragent

middlewares.py

from fake_useragent import UserAgent
class RandomUserAgentMiddleware(object):

    def __init__(self,crawler):
        super(RandomUserAgentMiddleware, self).__init__()
        self.ua = UserAgent()
        self.ua_type = crawler.settings.get('RANDOM_UA_TYPE','random')

    @classmethod
    def from_crawler(cls,crawler):
        return cls(crawler)

    def process_request(self,request,spider):

        def get_ua():
            return getattr(self.ua,self.ua_type)
        request.headers.setdefault('User-Agent',get_ua())

settings.py

settings.py启用中间件

RANDOM_UA_TYPE= 'random'

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
    #'tutorial.middlewares.TutorialDownloaderMiddleware': 1,
    'tutorial.middlewares.RandomUserAgentMiddleware': 543,
}

结果如下
fake-useragent

GitHub源码

相关推荐
©️2020 CSDN 皮肤主题: Age of Ai 设计师:meimeiellie 返回首页