pip install scrapy

def parse(self, response):
  with open("teark.html", "w") as f:
    f.write(response.text)

def parse(self, response):
  for _ in response.xpath("//div[@class='teark_article']"):
    item = ItcastItem()
    title = each.xpath("h3/text()").extract()
    content = each.xpath("p/text()").extract()
    item['title'] = title[0]
    item['content'] = content[0]
    yield item

scrapy shell "https://www.cnblogs.com/teark/"
response.xpath('//*[@class="even"]')
print site[0].xpath('./td[2]/text()').extract()[0]

import json

class ItcastJsonPipeline(object):

  def __init__(self):
    self.file = open('demo.json', 'wb')

  def process_item(self, item, spider):
    content = json.dumps(dict(item), ensure_ascii=False) + "\n"
    self.file.write(content)
    return item

  def close_spider(self, spider):
    self.file.close()

ITEM_PIPELINES = {
  "demoSpider.pipelines.DemoJsonPipeline":300
}

scrapy shell "http://teark.com/article.php"

from scrapy.linkextractors import LinkExtractor

# 注意转义字符&
page_lx = LinkExtractor(allow=('comment.php"htmlcode">

#提取匹配 'http://teark.com/article.php"htmlcode">

LOG_FILE = "DemoSpider.log"

# 还有CRITICAL, ERROR, WARNING DEBUG等级别
LOG_LEVEL = "INFO"


FormRequest


该方法用来发送POST请求，在spider.py中如下：


def start_requests(self):
    url = 'http://www.renren.com/PLogin.do'
    yield scrapy.FormRequest(
      url = url,
      formdata = {"email" : "teark@9133***34.com", "password" : "**teark**"},
      callback = self.parse_page
    )


模拟登陆：


import scrapy

class LoginSpider(scrapy.Spider):
  name = 'demo.com'
  start_urls = ['http://www.demo.com/users/login.php']　　　　

  def parse(self, response):
    return scrapy.FormRequest.from_response(
      response,
      formdata={'username': 'teark', 'password': '***'},
      callback=self.after_login
    )

  def after_login(self, response):
    # 检查登陆成功还是失败
    if "authentication failed" in response.body:
      self.log("Login failed", level=log.ERROR)
      return


Downloader Middlewares


防止爬虫被反策略


设置随机User-Agent
禁用Cookies，可以通过COOKIES_ENABLED 控制 CookiesMiddleware 开启或关闭
设置延迟下载降低频率
使用谷歌/百度等搜索引擎服务器页面缓存获取页面数据
使用IP地址池——VPN和代理IP
使用cralera（专用于爬虫的代理组件），配置中间件后请求都是通过crawlera发出的
设置下载中间件——Downloader Middlewares


键为中间件类的路径，值为其中间件的顺序(order)


DOWNLOADER_MIDDLEWARES = {
  'mySpider.middlewares.MyDownloaderMiddleware': 543,
}


当请求通过下载中间件时，process_request方法被调用；当下载中间件完成请求后传递响应给引擎时process_response方法被调用。
在settings.py同级目录下创建middlewares.py文件，如：


import random
import base64
from settings import USER_AGENTS
from settings import PROXIES


class RandomUserAgent(object):
  def process_request(self, request, spider):
    useragent = random.choice(USER_AGENTS)
    request.headers.setdefault("User-Agent", useragent)

class RandomProxy(object):
  def process_request(self, request, spider):
    proxy = random.choice(PROXIES)
    if proxy['user_passwd'] is None:
      request.meta['proxy'] = "http://" + proxy['ip_port']
    else:
      base64_userpasswd = base64.b64encode(proxy['user_passwd'])
      request.headers['Proxy-Authorization'] = 'Basic ' + base64_userpasswd
      request.meta['proxy'] = "http://" + proxy['ip_port']


与代理服务器连接需要使用base64编码，如果有需要身份验证的话还需要加上授权信息，
修改settings.py配置USER_AGENTS和PROXIES


免费代理IP上网搜，或购买可用的私密代理IP


USER_AGENTS = ["Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
  "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
  "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5"
  ]

PROXIES = [
　　{'ip_port': '111.8.60.9:8123', 'user_passwd': 'user1:pass1'},
　　{'ip_port': '101.71.27.120:80', 'user_passwd': 'user2:pass2'},
　　{'ip_port': '122.96.59.104:80', 'user_passwd': 'user3:pass3'},
　　]

# 禁用cookies
COOKIES_ENABLED = False

# 设置下载延迟
DOWNLOAD_DELAY = 3

# 添加自己编写的下载中间件
DOWNLOADER_MIDDLEWARES = {
  #'mySpider.middlewares.MyCustomDownloaderMiddleware': 543,
  'mySpider.middlewares.RandomUserAgent': 1,
  'mySpider.middlewares.ProxyMiddleware': 100
}


Scrapyd - 爬虫的远程部署和监控


安装Scrapyd


sudo pip install scrapyd
sudo pip install scrapyd-client


修改scrapyd的配置文件


启用scrapyd配置，在deploy后面指定当前项目的Scrapyd配置名，配置Scrapyd服务的ip和port，以及当前项目的项目名，如：


sudo vi /usr/local/lib/python3.8.6/site-packages/scrapyd/default_scrapyd.conf




# scrapy项目的settings文件位置，不用改动
[settings]
default = Demo.settings

# Scrapyd_Tencent是配置名
[deploy:Scrapyd_Demo]    

# 若是本机Scrapyd服务部署，则使用localhost即可否则使用服务主机的ip
url = http://localhost:6800/  

# 需要部署和监控的Scrapy项目名
project = Demo


通过Scrapyd客户端工具挂载项目


指令：scrapyd-deploy Scrapyd_Demo -p Demo
scrapyd-deploy 是客户端命令，参数是 Scrapyd配置名，以及 -p 指定项目名
远程部署和停止爬虫


部署：curl http://localhost:6800/schedule.json -d project=Demo -d spider=demo
停止：curl http://localhost:6800/cancel.json -d project=Demo -d job=iundsw....
注：爬虫启动成功后，会生成job值，停止爬虫时需要通过job值停止。
以上就是python Scrapy爬虫框架的使用的详细内容，更多关于python Scrapy爬虫框架的资料请关注其它相关文章！