使用scrapy框架爬取糗事百科全部段子数据

项目结构：

qsbk_spider.py

# -*- coding: utf-8 -*-
import scrapy
#爬虫开始  scrapy crawl qsbk_spider
from qsbk.items import QsbkItem


class QsbkSpiderSpider(scrapy.Spider):
    # 爬虫名称
    name = 'qsbk_spider'
    # 域名
    allowed_domains = ['qiushibaike.com']
    # 开始url 可以传递多个
    start_urls = ['https://www.qiushibaike.com/text/page/1/']
    crawl_domain= 'https://www.qiushibaike.com'

    def parse(self, response):
        print("=" * 40)
        #<class 'scrapy.http.response.html.HtmlResponse'>
        print(type(response))
        print("=" * 40)
        # xpath方式解析元素
        hrefList = response.xpath("//div[@id='content']//a[@class='contentHerf']/@href").getall()
        for href in hrefList:
            print(self.crawl_domain + href)
            yield scrapy.Request(self.crawl_domain + href,callback=self.getContent)
        next_url = response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get()
        if not next_url:
            # 程序结束
            return
        else:
            # 发送下一页请求
            yield scrapy.Request(self.crawl_domain + next_url,callback=self.parse)

    def getContent(self, response):
        content = response.xpath("//div[@id='content']//div[@class='content']/text()").getall()
        print(content)
        # 将数据放入一个对象里面
        item = QsbkItem(duanzi = content)
        # 将数据返回给管道
        yield item

item.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class QsbkItem(scrapy.Item):
    # define the fields for your item here like:
    duanzi = scrapy.Field()

pipelines.py

# -*- coding: utf-8 -*-

# define 定义
# 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

import json
#存储数据的地方
class QsbkPipeline(object):
    def __init__(self):
        self.fp = open("duanzi.json","w",encoding="utf-8")

    def open_spider(self,spider):
        print("爬虫开始了...")

    def process_item(self, item, spider):
        #接收parse函数返回的数据
        item_json = json.dumps(dict(item),ensure_ascii=False)
        #\n代表换行
        self.fp.write(item_json+"\n")
        return item

    def close_spider(self,spider):
        self.fp.close()
        print("爬虫结束了...")

settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for qsbk 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

#配置文件
BOT_NAME = 'qsbk'

SPIDER_MODULES = ['qsbk.spiders']
NEWSPIDER_MODULE = 'qsbk.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'qsbk (+http://www.yourdomain.com)'

# Obey robots.txt rules
# 1.是否遵守机器人协议 我们改为false
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
#设置下载延迟1秒
DOWNLOAD_DELAY = 1
# 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:
# 2.设置请求头
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 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'
}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'qsbk.middlewares.QsbkSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'qsbk.middlewares.QsbkDownloaderMiddleware': 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
#打开管道
ITEM_PIPELINES = {
    #300代表优先级 值越小代表优先级越高
   'qsbk.pipelines.QsbkPipeline': 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'

startCrawlProject.py

from scrapy import cmdline

#直接运行这个文件 不需要在命令行敲scrapy crawl qsbk_spider代码
cmdline.execute(['scrapy','crawl','qsbk_spider'])