首页 > > 网络编程 > 其它 >

scrapy 一些设置和问题

2019-02-20 00:46:06来源：博客园阅读 ()

scrapy设置ua池

设置后在setting启用

DOWNLOADER_MIDDLEWARES = {
   'laogou.middlewares.LaogouDownloaderMiddleware': 543,
   'laogou.middlewares.randomUserAgentMiddleware': 400,
   'laogou.middlewares.randomProxyMiddleware': 400，

from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware

class randomUserAgentMiddleware(UserAgentMiddleware):

    def __init__(self,user_agent=''):
        self.user_agent = user_agent

    def process_request(self, request, spider):
        ua = random.choice(self.user_agent_list)
        if ua:
            request.headers.setdefault('User-Agent', ua)
    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/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"
    ]

scrapy设置ip池

from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware

class randomHttpProxyMiddleware(HttpProxyMiddleware):
    def __init__(self,ip = ''):
        self.ip = ip
    def process_request(self, request, spider):
        ip = random.choice(self.ip_list)
        if ip:
            request.meta['proxy'] = ip
    ip_list = [
        'https://182.122.176.49:9999',
        'https://125.123.141.20:9999'
    ]

scrapy 设置自定义cookie：class LaogouwangSpider(scrapy.Spider):

　　 name = 'laogouwang'    
　　 # allowed_domains = ['www.laogou.com']    
　　 # start_urls = ['http://www.laogou.com/']

    def start_requests(self):
        url = 'https://www.lagou.com/'
        yield scrapy.Request(url=url,callback=self.parse,meta={'cookiejar':1})

    def parse(self, response):
        print(response.request.headers.getlist('Cookie'))
        print(response.headers.getlist('Set-Cookie'))
        url = 'https://www.lagou.com/jobs/list_'+ str(settings.keys) +'?city='+ str(settings.cidy) +'&cl=false&fromSearch=true&labelWords=&suginput='
        print(response.meta['cookiejar'])

        yield scrapy.Request(url=url,callback=self.download,meta={'cookiejar':response.meta['cookiejar']，'id':1},dont_filter=True)
　　 def download(self, response):

    # print(response.text)
    print(response.request.headers.getlist('Cookie'))
    print(response.headers.getlist('Set-Cookie'))
    i = response.meta.get('id')
    file = 'false'
    if i == 1:
        file = 'true'
    data = {
        "first":file,
        "pn":str(i),
        "kd":str(settings.keys)
    }
    headers_post = {
        'Accept': 'application/json, text/javascript, */*; q=0.01',
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        'Content-Length': str(len(urllib.parse.urlencode(data))),
        'Connection': 'keep-alive',
        'Referer':str(response.url),
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:65.0) Gecko/20100101 Firefox/65.0',
   }
    print(headers_post)
    print(str(response.url))
    print(data)
    url = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'

    yield scrapy.FormRequest(url=url,formdata=data,headers=headers_post,callback=self.files,dont_filter=True,meta={'cookiejar':True,'dont_redirect': True,'handle_httpstatus_list': [301,302]})

meta={'cookiejar':1}这个是启动cookei记录，在后面的请求中使用'cookiejar':response.meta['cookiejar']可以更新cookie。
注意，需要在setting中设置COOKIES_ENABLED = True

获取请求cookies是response.request.headers.getlist('Cookie')，响应cookies是response.headers.getlist('Set-Cookie')。
静止重定向dont_filter=True。
在meta里使用'dont_redirect': True,'handle_httpstatus_list': [301,302]可以在当前scrapy请求里禁用重定向。

scrapy 使用日志

import datetime,os
time = datetime.datetime.now().strftime('%Y_%m_%H_%M_%S')
LOG_FILE = 'logs'+ os.sep +str(time) + '_' + "laogou.log"
LOG_LEVEL = "DEBUG"
LOG_STDOUT = true

scrapy提供五种日志级别。

1.CRITICAL -- 关键错误
2.ERROR -- 一般级别的错误
3.WARNING -- 警告信息
4.INFO -- 信息消息的日志（建议生产模式使用）
5.DEBUG -- 调试消息的日志（建议开发模式）

LOG_FILE 用于日志输出记录的文件名 默认None
LOG_LEVEL 要记录的最低级别 默认DEBUG
LOG_STDOUT 如果为true 则进程的所有标准输出和错误都重定向到日志，列如print（） 默认false

使用文件启动spider

#laogoustrart.py

from laogou.spiders.laogouwang import LaogouwangSpider
from scrapy.crawler import CrawlerProcess
from scrapy.utils.project import get_project_settings

process = CrawlerProcess(get_project_settings())
process.crawl(LaogouwangSpider)
process.start()