scrapy基本操作

安裝：pip install scrapy

創建一個工程 ： scrapy startproject xxPro

cd xxPro

在spiders中創建一個爬蟲文件

-- scrapy genspider spiderName www.xxx.com

執行工程：

--- scrapy crawl spiderName

pipelines.py 文件
​
# 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
​
# 存儲文件
import pymysql
class AaproPipeline:
    # 專門用來處理item類型的對象
    # 該方法可以接受爬蟲文件提交過來的item對象
    # 該方法每接收到一個item就會被調用一次
    fp=None
    # 該方法的只需要調用一次
    def open_spider(self,spider):
        print('開始爬蟲....')
        self.fp=open('./t.txt','w',encoding='utf-8')
    def process_item(self, item, spider):
        tit = item['tit']
        cont = item['cont']
        self.fp.write(tit+':'+cont+'\n')
        return item # 這個return item 反回的值會傳入下一個執行的管道類
    def close_spider(self,spider):
        self.fp.close()
​
# 存儲數據庫
class mysqlPileLine(object):
    coon=None
    cursor = None
    def open_spider(self,spider):
        self.coon=pymysql.Connect(host='127.0.0.1',port=3306,user='root',password='123456',db='tet',charset='utf8')
    def process_item(self,item, spider):
        self.cursor = self.coon.cursor()
        try:
            self.cursor.execute('insert into qiub values("%s","%s")'%(item["tit"],item["cont"]))
            self.coon.commit()
        except Exception as e:
            print(e)
            self.coon.rollback()
        return item # 傳給下一個執行的管道類
    def close_spider(self,spider):
        self.cursor.close()
        self.coon.close()
​

 

settings.py 文件
# Scrapy settings for aaPro 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 = 'aaPro'
​
SPIDER_MODULES = ['aaPro.spiders']
NEWSPIDER_MODULE = 'aaPro.spiders'
​
​
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# UA 偽裝
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36'
​
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
​
LOG_LEVEL='ERROR'
# 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 = {
#   'aaPro.middlewares.AaproSpiderMiddleware': 543,
#}
​
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#   'aaPro.middlewares.AaproDownloaderMiddleware': 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 = {
   # 300 表示的是優先級，數值越小優先級越高
   'aaPro.pipelines.AaproPipeline': 300,
   'aaPro.pipelines.mysqlPileLine': 301,
​
}
​
# 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'
​

 

爬蟲文件.py
# Scrapy settings for aaPro 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 = 'aaPro'
​
SPIDER_MODULES = ['aaPro.spiders']
NEWSPIDER_MODULE = 'aaPro.spiders'
​
​
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# UA 偽裝
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36'
​
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
​
LOG_LEVEL='ERROR'
# 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 = {
#   'aaPro.middlewares.AaproSpiderMiddleware': 543,
#}
​
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#   'aaPro.middlewares.AaproDownloaderMiddleware': 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 = {
   # 300 表示的是優先級，數值越小優先級越高
   'aaPro.pipelines.AaproPipeline': 300,
   'aaPro.pipelines.mysqlPileLine': 301,
​
}
​
# 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'
​

 

 

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 AaproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    tit = scrapy.Field()
    cont = scrapy.Field()
​