Python爬虫之运用scrapy框架将爬取的内容存入文件和数据库

Posted 2021-09-04 汤米先生

文章目录

• 前言
• 源码
• • 爬虫文件（test1）
  • pipelines.py
  • setting.py
• 运行结果

---

前言

主要运用了scrapy持久化存储操作，下面主要展示spider和管道文件及一些设置。

源码

爬取的是itcast师资信息http://www.itcast.cn/channel/teacher.shtml#ajavaee

爬虫文件（test1）

这部分主要是对内容解析

import scrapy


class Test1Spider(scrapy.Spider):
    name = 'test1'
    # allowed_domains = ['https://www.baidu.com/']
    start_urls = ['http://www.itcast.cn/channel/teacher.shtml#ajavaee']

    def parse(self, response):
        li_list = response.xpath('/html/body/div[10]/div/div[2]/ul/li')
        for li in li_list:
            item={}
            item["name"] = li.xpath(".//h2/text()").extract_first()
            if li.xpath(".//p/span[2]/text()").extract_first()!= None:
                item["title"] = li.xpath(".//p/span[1]/text()").extract_first() + li.xpath(".//p/span[2]/text()").extract_first()
            else:
                item["title"]= li.xpath(".//p/span[1]/text()").extract_first()
            yield item

pipelines.py

这部分是对解析后的内容进行持久化存储

# 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
#存储到文件中
class TestprojectPipeline:
    fp =None
    def open_spider(self,spider):
        print("开始爬虫......")
        self.fp = open('./shizi.text','w',encoding='utf-8')
    def process_item(self, item, spider):
        author = item['name']
        content = item['title']
        self.fp.write(author+':'+content+'\\n')
        return item
    def close_spider(self,spider):
        print("爬虫结束！")
        self.fp.close()
  #存储到数据库中
class mysqlPileLine(object):
    conn = None
    cursor = None
    def open_spider(self,spider):
        self.conn = pymysql.Connect(host='127.0.0.1',port=3306,user='root',password='zpx',db='pydata',charset='utf8')
    def process_item(self,item,spider):
        self.cursor = self.conn.cursor()
        try:
            self.cursor.execute('insert into shizi value ("%s","%s")'%(item["name"],item["title"]))
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()

        return item

    def close_spider(self,spider):
        self.cursor.close()
        self.conn.close()

setting.py

# Scrapy settings for testproject 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 = 'testproject'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.17 (KHTML, like Gecko) Version/12.0.1  Safari/605.1.17"

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

LOG_LEVEL= 'WARNING' 
#显示的日志等级

# 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 = {
#    'testproject.middlewares.TestprojectSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'testproject.middlewares.TestprojectDownloaderMiddleware': 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 = {
   'testproject.pipelines.TestprojectPipeline': 300,
   'testproject.pipelines.mysqlPileLine': 301,
   #两种持久化存储的优先级，数越小，优先级越高
}

# 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