python scrapy 爬虫 初学

环境

python3.6.1 

scrapy

 

安装

pip3 install scrapy

新建项目(比如爬 豆瓣)

scrapy startproject douban

 

代码结构

新建spider 爬虫主文件

spider 目录 scrapy genspider douban_spider movie.douban.com

 

然后看看主要代码

spiders 目录下 douban_spider.py 文件

 

# -*- coding: utf-8 -*-
import scrapy
from douban.items import DoubanItem

class DoubanSpiderSpider(scrapy.Spider):
    #爬虫名
    name = 'douban_spider'
    allowed_domains = ['movie.douban.com']
    start_urls = ['http://movie.douban.com/top250']

    def parse(self, response):
        print(response.text)
        movie_list = response.xpath("//div[@class='article']//ol[@class='grid_view']/li")
        for i_ietm in movie_list:
            douban_item = DoubanItem()
            douban_item['serial_number'] = i_ietm.xpath(".//div[@class='item']//em/text()").extract_first()
            douban_item['movie_name'] = i_ietm.xpath(".//div[@class='item']//div[@class='info']/div/a/span[1]/text()").extract_first()
            content = i_ietm.xpath(".//div[@class='item']//div[@class='info']/div[@class='bd']/p[1]/text()").extract_first()
            #for i_content in content:
            douban_item['introduce'] = content
            douban_item['star'] = i_ietm.xpath(".//div[@class='item']//div[@class='info']/div[@class='bd']/div[@class='star']/span[2]/text()").extract_first()
            douban_item['evaluate'] = i_ietm.xpath(".//div[@class='item']//div[@class='info']/div[@class='bd']/div[@class='star']/span[4]/text()").extract_first()
            douban_item['describe'] = i_ietm.xpath(".//div[@class='item']//div[@class='info']/div[@class='bd']/p[@class='quote']/span/text()").extract_first()
            print(douban_item)
            if douban_item:
                yield douban_item
        next_link = response.xpath("//div[@class='paginator']//span[@class='next']/a/@href").extract_first()

        if next_link:
            #next_link = next_link[0]
            print('---', next_link)
            yield scrapy.Request("https://movie.douban.com/top250"+next_link, callback=self.parse)

　　

 

主体代码已经写完了

然后在看看配置 , 这个是为了防止目标网站 拦截 

settings.py 这个文件

USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'

　　

SPIDER_MIDDLEWARES = {
   #'douban.middlewares.DoubanSpiderMiddleware': 543,
    'douban.middlewares.my_useragent': 543,
}

　

my_useragent 这个配置是设置自定义的 useragent 
需要自己写一个类  在 middlewares.py 文件里面

 





class my_useragent(object):
    def process_request(self, request, splider):
        USER_AGENT_LIST = [
            "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
            "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
            "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
            "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
            "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
            "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
            "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
            "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
            "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",
            "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
            "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
            "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
            "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
            "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
            "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
            "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
            "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
            "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
            "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
            "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
            "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
            "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
        ]
        agent = random.choice(USER_AGENT_LIST)
        request.headers['User-Agent'] = agent





　　


　


然后 一次执行 main,py 和 执行命令


scrapy crawl douban_spider -o test.json  (这个是下载器数据)


 






            

            
posted @ 
2018-07-31 18:30 
风动随心 
阅读(338) 
评论(0) 
编辑 
收藏 
举报