settings.py中一些东西的含义可以看一下这里

python的scrapy框架的使用 和xpath的使用 && scrapy中request和response的函数参数 && parse()函数运行机制 

目录结构

创建一个scrapy项目（最后那个js是你创建项目的名字）

scrapy startprojects js

创建以crawl为模板的爬虫

scrapy genspider -t crawl jianshu wwww.jianshu.com

一、使用scrapy的crawl模板来创建一个爬虫jianshu.py文件

import scrapy

from scrapy.linkextractors import LinkExtractor

from scrapy.spiders import CrawlSpider, Rule

from js.items import JsItem

class JianshuSpider(CrawlSpider):

    # 运行scrapy时候的名字

    name = 'jianshu'

    allowed_domains = ['jianshu.com']

    start_urls = ['https://www.jianshu.com']

    rules = (

        # 要爬取网页上的推荐文章，进而可以使用crawl爬取我们规定的链接

        # 网页上的推荐文章链接是“/p/(12个【字母/数字】)”

        Rule(LinkExtractor(allow=r'.*?p/.*?'), callback='parse_detail', follow=True),

    )

    def parse_detail(self, response):

        # print(response.text())

        # print('-'*30)

        passage_id = response.url

        title = response.xpath('//h1[@class="_1RuRku"]/text()').get()

        time = response.xpath('//div[@class="s-dsoj"]/time/text()').get()

        author = response.xpath('//span[@class="FxYr8x"]/a/text()').get()

        body = response.xpath('//article[@class="_2rhmJa"]').get()

        type = response.xpath('//div[@class="_2Nttfz"]/a/img/text()').getall()

        type = ','.join(type)

        # 比如文章链接为https://www.jianshu.com/p/ef7bb28258c8

        # 那么文章的id，passage_id就是ef7bb28258c8，因为有的链接后面还有跟上“？参数”，所以我们先按照“？”

        # 切割链接，然后再取出文章id

        passage_id = passage_id.split('?')[0]

        passage_id = passage_id.split('/')[-1]

        # 有些文章违规在简书上不能看，但是链接还存在，所以我们需要判断一下

        if author == None:

            pass

        else: # 只要返回的对象是item类型，无论在那个函数里面返回都是返回到pipelines.py的item参数里面

            item = JsItem(

                passage_id = passage_id,

                title = title,

                time = time,

                author = author,

                body = body,

                type = type

            )

            yield item

二、item.py

# Define here the models for your scraped items

#

# See documentation in:

# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy

# 定义一下Item的对象的一些变量

class JsItem(scrapy.Item):

    passage_id = scrapy.Field()

    title = scrapy.Field()

    time = scrapy.Field()

    author = scrapy.Field()

    body = scrapy.Field()

    type = scrapy.Field()

三、start.py (启动程序)

from scrapy import cmdline

# jianshu是你的爬虫程序文件，注意要把这个命令用split拆开

cmdline.execute("scrapy crawl jianshu".split())

四、pipelines.py

# Define your item pipelines here

#

# Don't forget to add your pipeline to the ITEM_PIPELINES setting

# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html

# useful for handling different item types with a single interface

from itemadapter import ItemAdapter

from twisted.enterprise import adbapi

import pymysql

# class JsPipeline:

#     def process_item(self, item, spider):

#         return item

class JianShuSpiderPipeline(object):

    def __init__(self):

        # 连接数据库的一些参数

        dpparams = {

            'host':'127.0.0.1',

            'port': 3306,

            'user':'root',

            'password':'your_password',

            'database':'jianshu',

            'charset':'utf8'

        }

        # 连接数据库

        self.conn = pymysql.connect(**dpparams)

        # 定义游标

        self.cursor = self.conn.cursor()

        self._sql = None

    @property # 定义属性

    def sql(self):

        if self._sql == None:

            self._sql = '''

            insert into jsw(passage_id,title,time,author,body,type) values(%s,%s,%s,%s,%s,%s)

            '''

            return self._sql

        else:

            return self._sql

    def process_item(self,item,spider):

        # 执行sql语句，并传参

        self.cursor.execute(self.sql,(item['passage_id'],item['title'],item['time'],item['author'],item['body'],item['type']))

        # 记得执行之后要提交

        self.conn.commit()

        # 必须返回，不返回就不会处理下一个item对象

        return item

# 异步向mysql中插入数据

# class JianShuTwistedPipeline:

#     def __init__(self):

#         dpparams = {

#             'host':'127.0.0.1',

#             'port': 3306,

#             'user':'root',

#             'password':'qu513712qu',

#             'database':'jianshu',

#             'charset':'utf-8'

#         }

#         self.dbpool = adbapi.Connection('pymysql',**dpparams)

#         self._sql = None

#

#     @property

#     def sql(self):

#         if self._sql == None:

#             self._sql = '''

#             insert into jsw values(%s,%s,%s,%s,%s,%s)

#             '''

#             return self._sql

#         else:

#             return self._sql

#

#     def process_item(self,item,spider):

#         # 把插入Insert函数放到runInteraction里面，插入数据就会变成异步的，如果直接执行函数就是异步执行了

#         # runInteraction会返回一个游标给Insert函数

#         defer = self.dbpool.runInteraction(self.Insert,item)

#         defer.addErrback(self.error,item,spider)

#

#     def Insert(self,cursor,item):

#         cursor.execute(self._sql,(item['passage_id'],item['title'],item['time'],item['author'],item['body'],item['type']))

#

#     def error(self,error,item,spider):

#         print('-'*30)

#         print('error')

#         print('-'*30)

五、setting.py

# Scrapy settings for js project

#

# For simplicity, this file contains only settings considered important or

# commonly used. You can find more settings consulting the documentation:

#

#     https://docs.scrapy.org/en/latest/topics/settings.html

#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html

#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'js'

SPIDER_MODULES = ['js.spiders']

NEWSPIDER_MODULE = 'js.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent

#USER_AGENT = 'js (+http://www.yourdomain.com)'

# Obey robots.txt rules

ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)

#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)

# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay

# See also autothrottle settings and docs

DOWNLOAD_DELAY = 3

# The download delay setting will honor only one of:

#CONCURRENT_REQUESTS_PER_DOMAIN = 16

#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)

#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)

#TELNETCONSOLE_ENABLED = False

# Override the default request headers:

DEFAULT_REQUEST_HEADERS = {

  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

  'Accept-Language': 'en',

  'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'

}

# Enable or disable spider middlewares

# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html

SPIDER_MIDDLEWARES = {

    # 'js.middlewares.JsSpiderMiddleware': 543,

   'js.middlewares.UserAgentMiddleWare': 543,

}

# Enable or disable downloader middlewares

# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html

DOWNLOADER_MIDDLEWARES = {

   # 'js.middlewares.JsDownloaderMiddleware': 543,

   'js.middlewares.SeleniumDownloadMiddleware': 543,

}

# Enable or disable extensions

# See https://docs.scrapy.org/en/latest/topics/extensions.html

#EXTENSIONS = {

#    'scrapy.extensions.telnet.TelnetConsole': None,

#}

# Configure item pipelines

# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html

ITEM_PIPELINES = {

    # 管道里面使用的存储数据的类

   'js.pipelines.JianShuSpiderPipeline': 300,

   # 'js.pipelines.JianShuTwistedPipeline': 300,

}

# Enable and configure the AutoThrottle extension (disabled by default)

# See https://docs.scrapy.org/en/latest/topics/autothrottle.html

#AUTOTHROTTLE_ENABLED = True

# The initial download delay

#AUTOTHROTTLE_START_DELAY = 5

# The maximum download delay to be set in case of high latencies

#AUTOTHROTTLE_MAX_DELAY = 60

# The average number of requests Scrapy should be sending in parallel to

# each remote server

#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:

#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)

# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings

#HTTPCACHE_ENABLED = True

#HTTPCACHE_EXPIRATION_SECS = 0

#HTTPCACHE_DIR = 'httpcache'

#HTTPCACHE_IGNORE_HTTP_CODES = []

#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

六、middlewares.py

# Define here the models for your spider middleware

#

# See documentation in:

# https://docs.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals

# useful for handling different item types with a single interface

from itemadapter import is_item, ItemAdapter

import random

from selenium import webdriver

import time

from scrapy.http.response.html import HtmlResponse

class JsSpiderMiddleware:

    # Not all methods need to be defined. If a method is not defined,

    # scrapy acts as if the spider middleware does not modify the

    # passed objects.

    @classmethod

    def from_crawler(cls, crawler):

        # This method is used by Scrapy to create your spiders.

        s = cls()

        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)

        return s

    def process_spider_input(self, response, spider):

        # Called for each response that goes through the spider

        # middleware and into the spider.

        # Should return None or raise an exception.

        return None

    def process_spider_output(self, response, result, spider):

        # Called with the results returned from the Spider, after

        # it has processed the response.

        # Must return an iterable of Request, or item objects.

        for i in result:

            yield i

    def process_spider_exception(self, response, exception, spider):

        # Called when a spider or process_spider_input() method

        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.

        pass

    def process_start_requests(self, start_requests, spider):

        # Called with the start requests of the spider, and works

        # similarly to the process_spider_output() method, except

        # that it doesn’t have a response associated.

        # Must return only requests (not items).

        for r in start_requests:

            yield r

    def spider_opened(self, spider):

        spider.logger.info('Spider opened: %s' % spider.name)

class JsDownloaderMiddleware:

    # Not all methods need to be defined. If a method is not defined,

    # scrapy acts as if the downloader middleware does not modify the

    # passed objects.

    @classmethod

    def from_crawler(cls, crawler):

        # This method is used by Scrapy to create your spiders.

        s = cls()

        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)

        return s

    def process_request(self, request, spider):

        # Called for each request that goes through the downloader

        # middleware.

        # Must either:

        # - return None: continue processing this request

        # - or return a Response object

        # - or return a Request object

        # - or raise IgnoreRequest: process_exception() methods of

        #   installed downloader middleware will be called

        return None

    def process_response(self, request, response, spider):

        # Called with the response returned from the downloader.

        # Must either;

        # - return a Response object

        # - return a Request object

        # - or raise IgnoreRequest

        return response

    def process_exception(self, request, exception, spider):

        # Called when a download handler or a process_request()

        # (from other downloader middleware) raises an exception.

        # Must either:

        # - return None: continue processing this exception

        # - return a Response object: stops process_exception() chain

        # - return a Request object: stops process_exception() chain

        pass

    def spider_opened(self, spider):

        spider.logger.info('Spider opened: %s' % spider.name)

class UserAgentMiddleWare:

    User_Agent = [

        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",

        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",

        "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",

        "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",

        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",

        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",

        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",

        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",

        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",

        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",

        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",

        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",

        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",

        "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",

        "Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",

        "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",

        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"

    ]

    def process_request(self,request,spider):

        user_agent = random.choice(self.User_Agent)

        request.headers['User-Agent'] = user_agent

class SeleniumDownloadMiddleware(object):

    # 通过selenium+chrome来爬取网页的一些动态加载的数据

    def __init__(self): # 将你的chrome.exe文件位置传给它

        self.driver = webdriver.Chrome(executable_path=r'D:\python-senium\chromedriver.exe')

    def process_request(self,request,spider):

        self.driver.get(request.url)

        time.sleep(2)

        try:

            while 1:  # 文章下面有文章分类，我们需要点击加载加载更多才可以找出来这篇文章的所有归属类型

                showmore = self.driver.find_element_by_class_name('anticon anticon-down')

                showmore.click()

                time.sleep(1)

                if not showmore:

                    break

        except:

            pass

        # 网页源码

        sourse = self.driver.page_source

        # 构造一个response对象，并返回给jianshu.py

        response = HtmlResponse(url=self.driver.current_url,body=sourse,request=request,encoding='utf-8')

        return response

使用scrapy爬取jian shu文章的更多相关文章

  1. Python3.6+Scrapy爬取知名技术文章网站

    爬取分析 伯乐在线已经提供了所有文章的接口,还有下一页的接口,所有我们可以直接爬取一页,再翻页爬. 环境搭建 Windows下安装Python: http://www.cnblogs.com/0bug ...

  2. 第4章 scrapy爬取知名技术文章网站(2)

    4-8~9 编写spider爬取jobbole的所有文章 # -*- coding: utf-8 -*- import re import scrapy import datetime from sc ...

  3. Scrapy爬取伯乐在线文章

    首先搭建虚拟环境,创建工程 scrapy startproject ArticleSpider cd ArticleSpider scrapy genspider jobbole blog.jobbo ...

  4. 第4章 scrapy爬取知名技术文章网站(1)

    4-1 scrapy安装以及目录结构介绍 安装scrapy可以看我另外一篇博文:Scrapy的安装--------Windows.linux.mac等操作平台,现在是在虚拟环境中安装可能有不同. 1. ...

  5. scrapy爬取伯乐在线文章数据

    创建项目 切换到ArticleSpider目录下创建爬虫文件 设置settings.py爬虫协议为False 编写启动爬虫文件main.py

  6. scrapy爬取cnblogs文章列表

    scrapy爬取cnblogs文章 目标任务 安装爬虫 创建爬虫 编写 items.py 编写 spiders/cnblogs.py 编写 pipelines.py 编写 settings.py 运行 ...

  7. Scrapy爬取美女图片 (原创)

    有半个月没有更新了,最近确实有点忙.先是华为的比赛,接着实验室又有项目,然后又学习了一些新的知识,所以没有更新文章.为了表达我的歉意,我给大家来一波福利... 今天咱们说的是爬虫框架.之前我使用pyt ...

  8. 【转载】教你分分钟学会用python爬虫框架Scrapy爬取心目中的女神

    原文:教你分分钟学会用python爬虫框架Scrapy爬取心目中的女神 本博文将带领你从入门到精通爬虫框架Scrapy,最终具备爬取任何网页的数据的能力.本文以校花网为例进行爬取,校花网:http:/ ...

  9. scrapy爬取全部知乎用户信息

    # -*- coding: utf-8 -*- # scrapy爬取全部知乎用户信息 # 1:是否遵守robbots_txt协议改为False # 2: 加入爬取所需的headers: user-ag ...

随机推荐

  1. Approach for Unsupervised Bug Report Summarization 无监督bug报告汇总方法

    AUSUM: approach for unsupervised bug report summarization 1. Abstract 解决的bug被归类以便未来参考 缺点是还是需要手动的去细读很 ...

  2. 【JavaWeb】Servlet 程序

    Servlet 程序 Servlet Servlet 是在 Web 服务器中运行的小型 Java 程序.Servlet 通常通过 HTTP(超文本传输​​协议)接收和响应来自 Web 客户端的请求. ...

  3. 【C++】《Effective C++》第九章

    杂项讨论 条款53:不要轻忽编译器的警告 请记住 严肃对待编译器发出的警告信息.努力在你的编译器的最高(最严苛)警告级别下争取"无任何警告"的容易. 不要过度依赖编译器的报警能力, ...

  4. LeetCode707 设计链表

    设计链表的实现.您可以选择使用单链表或双链表.单链表中的节点应该具有两个属性:val 和 next.val 是当前节点的值,next 是指向下一个节点的指针/引用.如果要使用双向链表,则还需要一个属性 ...

  5. Oracle 索引原理分析

    索引是一种允许直接访问数据表中某一数据行的树型结构,为了提高查询效率而引入,是一个独立于表的对象,可以存放在与表不同的表空间中.索引记录中存有索引关键字和指向表中数据的指针(地址).对索引进行的I/O ...

  6. [工作札记]03: 微软Winform窗体中ListView、DataGridView等控件的Bug，会导致程序编译失败，影响范围：到最新的.net4.7.2都有

    工作中,我们发现了微软.net WinForm的一个Bug,会导致窗体设计器自动生成的代码失效,这个Bug从.net4.5到最新的.net4.7.2都存在,一直没有解决.最初是我在教学工作中发现的,后 ...

  7. 超精讲-逐例分析CS:LAB2-Bomb!(上）

    0. 环境要求 关于环境已经在lab1里配置过了这里要记得安装gdb 安装命令 sudo yum install gdb 实验的下载地址 http://csapp.cs.cmu.edu/3e/labs ...

  8. 为什么[] == false 为true

    首先要讲一下js的数据类型分为: 1.基本数据类型(原始数据类型):String.Boolean.Number.null.undefined.Symbol 2.引用数据类型:Object.Array. ...

  9. Pytorch 中张量的理解

    张量是一棵树 长久以来,张量和其中维度的概念把我搞的晕头转向. 一维的张量是数组,二维的张量是矩阵,这也很有道理. 但是给一个二维张量,让我算出它每一行的和,应该用 sum(dim=0) 还是 sum ...

  10. 低功耗降线性稳压器，24V转5V降压芯片

    PW2330开发了一种高效率的同步降压DC-DC变换器3A输出电流.PW2330在4.5V到30V的宽输入电压范围内工作集成主开关和同步开关,具有非常低的RDS(ON)以最小化传导 损失.PW2330 ...