（爬虫）Python课程设计：使用Scrapy框架实现二手车信息爬取

Scrapy 爬虫

完整项目：https://gitee.com/Hardman233/my-student-base/tree/master/esc
本项目只实现了爬取简单的静态网页并将数据存储到excel里。
如果只是快速启动本项目，可直接从项目启动看起。
该项目只用于学习使用，转载请标明出处，如有错误请指正。

环境安装

1. lxml   安装: pip install lxml
2. pyOpenSSL 安装：pip install pyOpenSSL
3. Twisted   安装：1.http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted
                   2.pip install Twisted‑xxx‑cpxx‑cpxxm‑win_amdxx.whl
                   注意： cpxx代表python版本 例如 cp37 == python3.7
4. pywin32   安装：pip install pywin32
5. scrapy    安装：pip install scrapy

验证成功

导入scrapy import scrapy 查看是否报错

创建项目

scrapy startproject <projectName>  # 创建一个scrapy项目 projectName = 项目名
cd projectName   # 进入该项目
scrapy genspider <spiderName> <domain>   # 创建爬虫文件 1.spiderName = 爬虫名, 
                                                       2.domain = 域名
例如：
scrapy startproject esc
cd esc
scrapy genspider ershouche che168.com    # 在你的spiders将会生成一个ershouche.py文件

项目启动

cd esc    # 进入项目
scrapy crawl ershouche     # 启动爬虫

项目结构

spiders/ershouche.py   （爬虫）解析数据文件
items.py   结构化数据文件
middlewares.py   整合中间件
pipelines.py （管道）存储数据文件
setting.py   全局配置文件

框架结构

文件说明

只会说明本项目文件中重点的代码的用法

ershouche.py

import scrapy
import re
from esc.items import EscItem
def checkdata(mylist):
    i = 0
    while i < len(mylist):
        list[i] += "万"
        i += 1


class ErshoucheSpider(scrapy.Spider):
    name = 'ershouche'
    allowed_domains = ['che168.com']
    start_urls = ['https://www.che168.com/china/bieke/a0_0msdgscncgpi1lto8csp1exx0/']
    # 根据规律手动获取url
    for link in range(2, 101):
        start_urls.append('https://www.che168.com/china/bieke/a0_0msdgscncgpi1lto8csp{lin}exx0/'.format(lin=link))

    def start_requests(self):
        for url in self.start_urls:
            print(url)
            yield scrapy.Request(
                url=url,
                callback=self.parse
            )

    def parse(self, response):
        li = response.xpath('/html/body/div[12]/div[1]/ul')
        i = 0
        flag = 0
        car = EscItem()

        for get_li in li:
            title = get_li.xpath("./li/a/div/h4/text()").extract()
            msg = get_li.xpath("./li/a/div/p/text()").extract()
            nowpri = get_li.xpath("./li/a/div/div/span/em/text()").extract()
            newpri = get_li.xpath("./li/a/div/div/s/text()").extract()
            # 处理数据
            while i < len(nowpri):
                nowpri[i] += '万'
                i += 1
            for j in range(len(title)):
                try:
                    car["title"] = title[j]
                    car["msg"] = msg[j]
                    car["nowpri"] = nowpri[j]
                    car["newpri"] = newpri[j]
                    flag += 1
                    print(title[j], msg[j], nowpri[j], newpri[j], "次数", flag)
                    yield car
                except Exception:
                    print("异常:", Exception.args)

    def parse_detail(self, resp, **kwargs):
        pass

属性：
    title  用于保存车辆型号及其款式
    msg    用于保存车辆信息：公里数、售卖地区、购买车辆时间等
    nowpri 用于保存当前二手车售卖价格
    newpri 用于保存该型号的车新车购买价格
        
语句：        
    start_urls = ['https://www.che168.com/china/bieke/a0_0msdgscncgpi1lto8csp1exx0/']
    # 根据规律手动获取url
    for link in range(2, 101):
        start_urls.append('https://www.che168.com/china/bieke/a0_0msdgscncgpi1lto8csp{lin}exx0/'.format(lin=link))
    # 如果想要爬取不同品牌的车辆，只需要将start_urls和append方法中的url中的bieke改为你想爬取的品牌的拼音即可 
    # 如果想要爬取不同地区的二手车，只需要将start_urls和append方法中的url中的china改为你想爬取的地区的拼音即可 
    # 该项目默认爬取的地区和品牌是全国、别克

    # 处理数据
            while i < len(nowpri):
                nowpri[i] += '万'
                i += 1
    # 该代码的目的是：由于获取当前价格只有数字而并没有‘万’字，故拼接

items.py

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

import scrapy


class EscItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    msg = scrapy.Field()
    nowpri = scrapy.Field()
    newpri = scrapy.Field()
    pass

结构化数据，主要用于规范数据

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 openpyxl import Workbook

class EscPipeline:
    def __init__(self):
        self.wb = Workbook()
        self.ws = self.wb.active
        self.ws.append(['型号', '信息', '新车价格', '当前价格'])

        # self.f = open("./二手车1.csv", mode="a", encoding="utf-8")
        # self.f.append(['型号', '信息', '当前价格', '新车价格'])

    def open_spider(self, spider):
        pass

    def close_spider(self, spider):
        # if self.ws:
        #     self.ws.close()
        pass

    def process_item(self, item, spider):
        line = [item['title'],item['msg'],item['newpri'],item['nowpri']]
        self.ws.append(line)
        self.wb.save('别克二手车.xlsx')
        # txt = str.format('{},{},{},{}\n',item['title'],item['msg'],item['newpri'],item['nowpri'])
        # self.ws.write(txt)
        return item

数据持久化，主要用于数据存储。

函数：
    def process_item(self, item, spider):
    line = [item['title'],item['msg'],item['newpri'],item['nowpri']]
    self.ws.append(line)
    # 修改保存的文件名
    self.wb.save('别克二手车.xlsx')
    return item

在这里只是用excel对数据进行存储，当然用mysql等数据库存储亦可
由于代码逻辑简单在这里将不在赘述

settings.py

# Scrapy settings for esc 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 = 'esc'

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


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

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

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

# 延时2秒，不能动态改变，时间间隔固定，容易被发现，导致ip被封
DOWNLOAD_DELAY = 2
# 启用后，当从相同的网站获取数据时，Scrapy将会等待一个随机的值，延迟时间为0.5到1.5之间的一个随机值乘以DOWNLOAD_DELAY
RANDOMIZE_DOWNLOAD_DELAY = True
# 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 = {
#    'esc.middlewares.EscSpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'esc.middlewares.EscDownloaderMiddleware': 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 = {
   'esc.pipelines.EscPipeline': 300,
}

FEED_EXPORT_ENCODING = 'gb18030'
# 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 = 2
# 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'

全局配置文件

# 是否遵守爬虫协议
  ROBOTSTXT_OBEY = False
  
# 设置显示日志等级
  LOG_LEVEL = "WARNING"
  
# 延时2秒，不能动态改变，时间间隔固定，容易被发现，导致ip被封
   DOWNLOAD_DELAY = 2
# 启用后，当从相同的网站获取数据时，Scrapy将会等待一个随机的值，延迟时间为0.5到1.5之间的一个随机值乘以DOWNLOAD_DELAY
   RANDOMIZE_DOWNLOAD_DELAY = True

# 开启管道
   ITEM_PIPELINES = {
       'esc.pipelines.EscPipeline': 300,
   }