本文已参与「新人创作礼」活动，一起开启掘金创作之路。

案例一:爬取豆瓣电影前250

首先创建scrapy项目.见: 创建一个Scrapy爬虫项目并运行 - 掘金 (juejin.cn) 编写爬虫:

import scrapy
from douban.items import  DoubanItem

class MovieSpider(scrapy.Spider):
    name = 'movie'
   # allowed_domains = ['www.xx.com']
    start_urls = ['http://movie.douban.com/top250']

    def parse(self, response):
        ranks = response.css('.pic>em::text').extract()
        names = response.css('.hd>a>span:first-child::text').extract()
        ratings = response.css('.rating_num::text').extract()
        for rank,name,rating in zip(ranks,names,ratings):
            item = DoubanItem()
            item['rank']= rank
            item['name'] = name
            item['rating'] = rating
            yield  item
        next_page_url = response.css('.next>a::attr(href)').extract_first()
        if next_page_url is not  None:
            yield  scrapy.Request(response.urljoin(next_page_url))

设置item模板，定义字段用于保存数据，在items.py中输入如下代码：

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class DoubanItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    rank = scrapy.Field()
    name = scrapy.Field()
    rating = scrapy.Field()

数据处理脚本，用于持久化存储，在pipelines.py中增加如下代码:

# 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
import  pymysql


class DoubanPipeline:
    db=None
    def open_spider(self,spider):
        self.db = pymysql.connect(host="localhost",user='root',password='20010608csm',db='第一次实验')

    def process_item(self, item, spider):
        cursor = self.db.cursor()#创建游标
        sql='insert into doubanmovie values(%s,%s,%s)'
        cursor.execute(sql,(str(item['rank']),item['name'],str(item['rating'])))
        self.db.commit()
        cursor.close()
        return item

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

设置配置文件，在settings.py中增加如下代码：

# Scrapy settings for douban 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 = 'douban'
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 Edg/98.0.1108.56"
SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'


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

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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',
#}

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

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'douban.middlewares.DoubanDownloaderMiddleware': 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 = {
   'douban.pipelines.DoubanPipeline': 300,
}
LOG_LEVEL = "WARNING"
# 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'

最后,运行爬虫.

结果如下:

案例二:爬取名人名言.

首先创建爬虫项目,然后编写Spider爬虫

import scrapy
class QuoteSpider(scrapy.Spider):
    name = 'quote'
    start_urls = ['http://quotes.toscrape.com/']
    def parse(self, response):
        quotelist=[]
        divs = response.xpath('//div[@class="quote"]')
        for div in divs:
            author = div.xpath('./span/small/text()').extract_first()
            text = div.xpath('./span[@class="text"]/text()').extract_first()
            dic = {
                'author':author,
                'text':text
            }
            quotelist.append(dic)
        return  quotelist

然后设置item模板，定义字段用于保存数据，在items.py中输入如下代码：

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

import scrapy


class MingItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    author= scrapy.Field
    text = scrapy.Field

数据处理脚本，用于持久化存储，在pipelines.py中增加如下代码：

# 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


class MingPipeline:
    fp = None
    def open_spider(self,spider):
        self.fp = open('quote.txt','w',encoding='utf-8')

    def process_item(self, item, spider):
        author= item['author']
        text = item['text']
        self.fp.write(author+":"+text+'\n')
        return item
    def close_spider(self,spider):
        self.fp.close()

设置配置文件，在settings.py中增加如下代码：

# Scrapy settings for ming 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 = 'ming'

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


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

# Obey robots.txt rules
ROBOTSTXT_OBEY = True
FEED_EXPOPT_ENCODING = 'gb18030'
ITEM_PIPELINES = {
    'ming.pipelines.MingPipeline':300,
}
LOG_LEVEL = 'WARNING'
# 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',
#}

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

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'ming.middlewares.MingDownloaderMiddleware': 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 = {
#    'ming.pipelines.MingPipeline': 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'

运行结果如下: