首页 > > 网络编程 > 其它 >

Python的scrapy之爬取6毛小说网的圣墟

2018-10-26 05:29:30来源：博客园阅读 ()

闲来无事想看个小说，打算下载到电脑上看，找了半天，没找到可以下载的网站，于是就想自己爬取一下小说内容并保存到本地

圣墟第一章沙漠中的彼岸花 - 辰东 - 6毛小说网 http://www.6mao.com/html/40/40184/12601161.html

这是要爬取的网页

观察结构

然后开始创建scrapy项目：

其中sixmaospider.py:

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


class SixmaospiderSpider(scrapy.Spider):
    name = 'sixmaospider'
    #allowed_domains = ['http://www.6mao.com']
    start_urls = ['http://www.6mao.com/html/40/40184/12601161.html']  #圣墟

    def parse(self, response):
        novel_biaoti = response.xpath('//div[@id="content"]/h1/text()').extract()
        #print(novel_biaoti)
        novel_neirong=response.xpath('//div[@id="neirong"]/text()').extract()
        print(novel_neirong)
        #print(len(novel_neirong))
        novelitem = SixmaoItem()
        novelitem['novel_biaoti'] = novel_biaoti[0]
        print(novelitem['novel_biaoti'])

        for i in range(0,len(novel_neirong),2):
            #print(novel_neirong[i])

            novelitem['novel_neirong'] = novel_neirong[i]

            yield novelitem

        #下一章
        nextPageURL = response.xpath('//div[@class="s_page"]/a/@href').extract()  # 取下一页的地址
        nexturl='http://www.6mao.com'+nextPageURL[2]
        print('下一章',nexturl)
        if nexturl:
            url = response.urljoin(nexturl)
            # 发送下一页请求并调用parse()函数继续解析
            yield scrapy.Request(url, self.parse, dont_filter=False)
            pass
        else:
            print("退出")
        pass

pipelinesio.py 将内容保存到本地文件

import os
print(os.getcwd())


class SixmaoPipeline(object):
    def process_item(self, item, spider):
        #print(item['novel'])

        with open('./data/圣墟.txt', 'a', encoding='utf-8') as fp:
            fp.write(item['novel_neirong'])
            fp.flush()
            fp.close()
        return item
    print('写入文件成功')

items.py

import scrapy


class SixmaoItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    novel_biaoti=scrapy.Field()
    novel_neirong=scrapy.Field()
    pass

startsixmao.py，直接右键这个运行，项目就开始运行了

from scrapy.cmdline import execute

execute(['scrapy', 'crawl', 'sixmaospider'])

settings.py

LOG_LEVEL='INFO'   #这是加日志
LOG_FILE='novel.log'

DOWNLOADER_MIDDLEWARES = {
    'sixmao.middlewares.SixmaoDownloaderMiddleware': 543,
    'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware' : None,
    'sixmao.rotate_useragent.RotateUserAgentMiddleware' :400  #这行是使用代理
}


ITEM_PIPELINES = {
    #'sixmao.pipelines.SixmaoPipeline': 300,
    'sixmao.pipelinesio.SixmaoPipeline': 300,

}  #在pipelines输出管道加入这个

SPIDER_MIDDLEWARES = {
   'sixmao.middlewares.SixmaoSpiderMiddleware': 543,
}  #打开中间件 其余地方应该不需要改变

rotate_useragent.py 给项目加代理，防止被服务器禁止

# 导入random模块
import random
# 导入useragent用户代理模块中的UserAgentMiddleware类
from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware

# RotateUserAgentMiddleware类，继承 UserAgentMiddleware 父类
# 作用：创建动态代理列表，随机选取列表中的用户代理头部信息，伪装请求。
#       绑定爬虫程序的每一次请求，一并发送到访问网址。

# 发爬虫技术：由于很多网站设置反爬虫技术，禁止爬虫程序直接访问网页，
#             因此需要创建动态代理，将爬虫程序模拟伪装成浏览器进行网页访问。
class RotateUserAgentMiddleware(UserAgentMiddleware):
    def __init__(self, user_agent=''):
        self.user_agent = user_agent

    def process_request(self, request, spider):
        #这句话用于随机轮换user-agent
        ua = random.choice(self.user_agent_list)
        if ua:
            # 输出自动轮换的user-agent
            print(ua)
            request.headers.setdefault('User-Agent', ua)

    # the default user_agent_list composes chrome,I E,firefox,Mozilla,opera,netscape
    # for more user agent strings,you can find it in http://www.useragentstring.com/pages/useragentstring.php
    # 编写头部请求代理列表
    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"
       ]