scrapy startproject xxx 创建项目
scrapy crawl xxxx -o xx.csv 保存csv格式在本地
Spriders爬虫文件创建 scrapy genspider xxx xxx.com（网站域名）

设置请求头的方法

一、手动添加单一UserAgent

1.第一种方法，单一方式，可用在非框架爬虫爬取简单量小的项目中。

headers = {
   'User-Agent':"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) 
Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3650.400 QQBrowser/10.4.3341.400"}#headers包含其他请求信息，一并传递给requests
response = requests.get(url, headers=headers)

2.第二种方法，在Scrapy框架中：改写两个地方
Settings.py

USER_AGENT_LIST = [
    'zspider/0.9-dev http://feedback.redkolibri.com/',
    'Xaldon_WebSpider/2.0.b1',
    'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) Speedy Spider (http://www.entireweb.com/about/search_tech/speedy_spider/)',
    'Mozilla/5.0 (compatible; Speedy Spider; http://www.entireweb.com/about/search_tech/speedy_spider/)',
    'Speedy Spider (Entireweb; Beta/1.3; http://www.entireweb.com/about/search_tech/speedyspider/)',
    'Speedy Spider (Entireweb; Beta/1.2; http://www.entireweb.com/about/search_tech/speedyspider/)',
    'Speedy Spider (Entireweb; Beta/1.1; http://www.entireweb.com/about/search_tech/speedyspider/)',
    'Speedy Spider (Entireweb; Beta/1.0; http://www.entireweb.com/about/search_tech/speedyspider/)',
    'Speedy Spider (Beta/1.0; www.entireweb.com)',
    'Speedy Spider (http://www.entireweb.com/about/search_tech/speedy_spider/)',
    'Speedy Spider (http://www.entireweb.com/about/search_tech/speedyspider/)',
    'Speedy Spider (http://www.entireweb.com)',
    'Sosospider+(+http://help.soso.com/webspider.htm)',
    'sogou spider',
    'Nusearch Spider (www.nusearch.com)',
    'nuSearch Spider (compatible; MSIE 4.01; Windows NT)',
    'lmspider (lmspider@scansoft.com)',
    'lmspider lmspider@scansoft.com',
    'ldspider (http://code.google.com/p/ldspider/wiki/Robots)',
    'iaskspider/2.0(+http://iask.com/help/help_index.html)',
    'iaskspider',
    'hl_ftien_spider_v1.1',
    'hl_ftien_spider',
    'FyberSpider (+http://www.fybersearch.com/fyberspider.php)',
    'FyberSpider',
    'everyfeed-spider/2.0 (http://www.everyfeed.com)',
    'envolk[ITS]spider/1.6 (+http://www.envolk.com/envolkspider.html)',
    'envolk[ITS]spider/1.6 ( http://www.envolk.com/envolkspider.html)',
    'Baiduspider+(+http://www.baidu.com/search/spider_jp.html)',
    'Baiduspider+(+http://www.baidu.com/search/spider.htm)',
    'BaiDuSpider',
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0) AddSugarSpiderBot www.idealobserver.com",
    "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 6.1) 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/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
    "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/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
    "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",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
    "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5",
    "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12",
    "Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.54 Safari/535.2",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
    "Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 ",
    "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.0.3) Gecko/2008092414 Firefox/3.0.3",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1) Gecko/20090624 Firefox/3.5",
    "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.14) Gecko/20110218 AlexaToolbar/alxf-2.0 Firefox/3.6.14",
    "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
    ]

DOWNLOADER_MIDDLEWARES = {
    'spider_douban.middlewares.RandomUserAgentMiddleware': 400,
    'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': None,
}

Middlewares.py 中添加

from spider_douban.settings import USER_AGENT_LIST
import random

class RandomUserAgentMiddleware():
    def process_request(self, request, spider):
        ua  = random.choice(USER_AGENT_LIST)
        if ua:
            request.headers.setdefault('User-Agent', ua)

3.第三种方法 使用fake_useragent包 pip安装
更新fake_useragent，在命令行中输入pip install -U fake-useragent即可完成更新

from fake_useragent import UserAgen

#请求的网址

url=”http://www.baidu.com”

#请求头

headers={“User-Agent”:UserAgent().random}
headers = {"User-Agent": UserAgent(use_cache_server=False).chrome}#禁用服务器缓存
ua = UserAgent(cache=False)#不缓存数据：
ua = UserAgent(verify_ssl=False)#忽略ssl验证：

#请求网址

response=requests.get(url=url,headers=headers)

#响应体内容

print(response.text)

#响应状态信息

print(response.status_code)

#响应头信息

print(response.headers)

二、储存到Mongo数据库

pipeline.py文件中如下

import pymongo

class MongoPipeline(object):
    def __init__(self,mongo_uri,mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db
        
    @classmethod
    def from_crawler(cls,crawler):
        return cls(
            mongo_uri = crawler.settings.get('MONGO_URI'),
            mongo_db = crawler.settings.get('MONGO_DB')
        )
        
    def open_spider(self,spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]
        
    def process_item(self,item,spider):
        name = item.__class__.__name__
        self.db[name].insert(dict(item))
        return item
    
    def close_spider(self,spider):
        self.client.close()

setting.py中添加

ITEM_PIPELINES = {
    
    'douban.pipelines.MongoPipeline':400,
    }
MONGO_URI = 'localhost'#数据库地址
MONGO_DB = 'douban' #数据库名字