Scrapy运行流程大概如下:
- 引擎从调度器中取出一个链接(URL)用于接下来的抓取
- 引擎把URL封装成一个请求(Request)传给下载器
- 下载器把资源下载下来,并封装成应答包(Response)
- 爬虫解析Response
- 解析出实体(Item),则交给实体管道进行进一步的处理
- 解析出的是链接(URL),则把URL交给调度器等待抓取
一、安装
因为python3并不能完全支持Scrapy,因此为了完美运行Scrapy,我们使用python2.7来编写和运行Scrapy。
注:windows平台需要依赖pywin32,请根据自己系统32/64位选择下载安装,https://sourceforge.net/projects/pywin32/
其它可能依赖的安装包:lxml-3.6.4-cp27-cp27m-win_amd64.whl,VCForPython27.msi百度下载即可
- scrapy.cfg 项目的配置信息,主要为Scrapy命令行工具提供一个基础的配置信息。(真正爬虫相关的配置信息在settings.py文件中)
- items.py 设置数据存储模板,用于结构化数据,如:Django的Model
- pipelines 数据处理行为,如:一般结构化的数据持久化
- settings.py 配置文件,如:递归的层数、并发数,延迟下载等
- spiders 爬虫目录,如:创建文件,编写爬虫规则
注意:一般创建爬虫文件时,以网站域名命名
- 1.爬虫文件需要定义一个类,并继承scrapy.spiders.Spider
- 2.必须定义name,即爬虫名,如果没有name,会报错。因为源码中是这样定义的:
- 3.编写函数parse,这里需要注意的是,该函数名不能改变,因为Scrapy源码中默认callback函数的函数名就是parse;
- 4.定义需要爬取的url,放在列表中,因为可以爬取多个url,Scrapy源码是一个For循环,从上到下爬取这些url,使用生成器迭代将url发送给下载器下载url的html。源码截图:
4、运行
进入p1目录,运行命令:
格式:scrapy crawl+爬虫名 –nolog即不显示日志
示例代码:
def parse ( self , response ) :
# 分析页面
# 找到页面中符合规则的内容(校花图片),保存
# 找到所有的a标签,再访问其他a标签,一层一层的搞下去
hxs = HtmlXPathSelector ( response ) #创建查询对象
# 如果url是 http://www.xiaohuar.com/list-1-\d+.html
if re . match ( 'http://www.xiaohuar.com/list-1-\d+.html' , response . url ) : #如果url能够匹配到需要爬取的url,即本站url
items = hxs . select ( '//div[@class="item_list infinite_scroll"]/div' ) #select中填写查询目标,按scrapy查询语法书写
for i in range ( len ( items ) ) :
src = hxs . select ( '//div[@class="item_list infinite_scroll"]/div[%d]//div[@class="img"]/a/img/@src' % i ) . extract ( ) #查询所有img标签的src属性,即获取校花图片地址
name = hxs . select ( '//div[@class="item_list infinite_scroll"]/div[%d]//div[@class="img"]/span/text()' % i ) . extract ( ) #获取span的文本内容,即校花姓名
school = hxs . select ( '//div[@class="item_list infinite_scroll"]/div[%d]//div[@class="img"]/div[@class="btns"]/a/text()' % i ) . extract ( ) #校花学校
if src :
ab_src = "http://www.xiaohuar.com" + src [ 0 ] #相对路径拼接
file_name = "%s_%s.jpg" % ( school [ 0 ] . encode ( 'utf-8' ) , name [ 0 ] . encode ( 'utf-8' ) ) #文件名,因为python27默认编码格式是unicode编码,因此我们需要编码成utf-8
file_path = os . path . join ( "/Users/wupeiqi/PycharmProjects/beauty/pic" , file_name )
urllib . urlretrieve ( ab_src , file_path )
注:urllib.urlretrieve(ab_src, file_path) ,接收文件路径和需要保存的路径,会自动去文件路径下载并保存到我们指定的本地路径。
5.递归爬取网页
上述代码仅仅实现了一个url的爬取,如果该url的爬取的内容中包含了其他url,而我们也想对其进行爬取,那么如何实现递归爬取网页呢?
示例代码:
即通过yield生成器向每一个url发送request请求,并执行返回函数parse,从而递归获取校花图片和校花姓名学校等信息。
注:可以修改settings.py 中的配置文件,以此来指定“递归”的层数,如: DEPTH_LIMIT = 1
6.scrapy查询语法中的正则:
from scrapy . selector import Selector
from scrapy . http import HtmlResponse
html = "" "<!DOCTYPE html>
<html>
<head lang=" en ">
<meta charset=" UTF - 8 ">
<title></title>
</head>
<body>
<li class=" item - "><a href=" link . html ">first item</a></li>
<li class=" item - 0 "><a href=" link1 . html ">first item</a></li>
<li class=" item - 1 "><a href=" link2 . html ">second item</a></li>
</body>
</html>
" ""
response = HtmlResponse ( url = 'http://example.com' , body = html , encoding = 'utf-8' )
ret = Selector ( response = response ) . xpath ( '//li[re:test(@class, "item-\d*")]//@href' ) . extract ( )
print ( ret )
语法规则:Selector(response=response查询对象).xpath(‘//li[re:test(@class, “item-d*”)]//@href’).extract(),即根据re正则匹配,test即匹配,属性名是class,匹配的正则表达式是”item-d*”,然后获取该标签的href属性。
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import scrapy
import hashlib
from tutorial . items import JinLuoSiItem
from scrapy . http import Request
from scrapy . selector import HtmlXPathSelector
class JinLuoSiSpider ( scrapy . spiders . Spider ) :
count = 0
url_set = set ( )
name = "jluosi"
domain = 'http://www.jluosi.com'
allowed_domains = [ "jluosi.com" ]
start_urls = [
"http://www.jluosi.com:80/ec/goodsDetail.action?jls=QjRDNEIzMzAzOEZFNEE3NQ==" ,
]
def parse ( self , response ) :
md5_obj = hashlib . md5 ( )
md5_obj . update ( response . url )
md5_url = md5_obj . hexdigest ( )
if md5_url in JinLuoSiSpider . url_set :
pass
else :
JinLuoSiSpider . url_set . add ( md5_url )
hxs = HtmlXPathSelector ( response )
if response . url . startswith ( 'http://www.jluosi.com:80/ec/goodsDetail.action' ) :
item = JinLuoSiItem ( )
item [ 'company' ] = hxs . select ( '//div[@class="ShopAddress"]/ul/li[1]/text()' ) . extract ( )
item [ 'link' ] = hxs . select ( '//div[@class="ShopAddress"]/ul/li[2]/text()' ) . extract ( )
item [ 'qq' ] = hxs . select ( '//div[@class="ShopAddress"]//a/@href' ) . re ( '.*uin=(?P<qq>\d*)&')
item [ 'address' ] = hxs . select ( '//div[@class="ShopAddress"]/ul/li[4]/text()' ) . extract ( )
item [ 'title' ] = hxs . select ( '//h1[@class="goodsDetail_goodsName"]/text()' ) . extract ( )
item [ 'unit' ] = hxs . select ( '//table[@class="R_WebDetail_content_tab"]//tr[1]//td[3]/text()' ) . extract ( )
product_list = [ ]
product_tr = hxs . select ( '//table[@class="R_WebDetail_content_tab"]//tr' )
for i in range ( 2 , len ( product_tr ) ) :
temp = {
'standard' : hxs . select ( '//table[@class="R_WebDetail_content_tab"]//tr[%d]//td[2]/text()' % i ). extract ( ) [ 0 ] . strip ( ) ,
'price' : hxs . select ( '//table[@class="R_WebDetail_content_tab"]//tr[%d]//td[3]/text()' % i ) . extract ( ) [ 0 ] . strip ( ) ,
}
product_list . append ( temp )
item [ 'product_list' ] = product_list
yield item
current_page_urls = hxs . select ( '//a/@href' ) . extract ( )
for i in range ( len ( current_page_urls ) ) :
url = current_page_urls [ i ]
if url . startswith ( 'http://www.jluosi.com' ) :
url_ab = url
yield Request ( url_ab , callback = self . parse )
选择器规则 Demo
选择器规则 Demo
选择器规则Demo
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import scrapy
import hashlib
from beauty . items import JieYiCaiItem
from scrapy . http import Request
from scrapy . selector import HtmlXPathSelector
from scrapy . spiders import CrawlSpider , Rule
from scrapy . linkextractors import LinkExtractor
class JieYiCaiSpider ( scrapy . spiders . Spider ) :
count = 0
url_set = set ( )
name = "jieyicai"
domain = 'http://www.jieyicai.com'
allowed_domains = [ "jieyicai.com" ]
start_urls = [
"http://www.jieyicai.com" ,
]
rules = [
#下面是符合规则的网址,但是不抓取内容,只是提取该页的链接(这里网址是虚构的,实际使用时请替换)
#Rule(SgmlLinkExtractor(allow=(r'http://test_url/test?page_index=\d+'))),
#下面是符合规则的网址,提取内容,(这里网址是虚构的,实际使用时请替换)
#Rule(LinkExtractor(allow=(r'http://www.jieyicai.com/Product/Detail.aspx?pid=\d+')), callback="parse"),
]
def parse ( self , response ) :
md5_obj = hashlib . md5 ( )
md5_obj . update ( response . url )
md5_url = md5_obj . hexdigest ( )
if md5_url in JieYiCaiSpider . url_set :
pass
else :
JieYiCaiSpider . url_set . add ( md5_url )
hxs = HtmlXPathSelector ( response )
if response . url . startswith ( 'http://www.jieyicai.com/Product/Detail.aspx' ) :
item = JieYiCaiItem ( )
item [ 'company' ] = hxs . select ( '//span[@class="username g-fs-14"]/text()' ) . extract ( )
item [ 'qq' ] = hxs . select ( '//span[@class="g-left bor1qq"]/a/@href' ) . re ( '.*uin=(?P<qq>\d*)&' )
item [ 'info' ] = hxs . select ( '//div[@class="padd20 bor1 comard"]/text()' ) . extract ( )
item [ 'more' ] = hxs . select ( '//li[@class="style4"]/a/@href' ) . extract ( )
item [ 'title' ] = hxs . select ( '//div[@class="g-left prodetail-text"]/h2/text()' ) . extract ( )
yield item
current_page_urls = hxs . select ( '//a/@href' ) . extract ( )
for i in range ( len ( current_page_urls ) ) :
url = current_page_urls [ i ]
if url . startswith ( '/' ) :
url_ab = JieYiCaiSpider . domain + url
yield Request ( url_ab , callback = self . parse )
spider
spider
spider
上述代码中:对url进行md5加密的目的是避免url过长,也方便保存在缓存或数据库中。
此处代码的关键在于:
-
将获取的数据封装在了Item对象中
-
yield Item对象 (一旦parse中执行yield Item对象,则自动将该对象交个pipelines的类来处理)
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from twisted . enterprise import adbapi
import MySQLdb . cursors
import re
mobile_re = re . compile ( r '(13[0-9]|15[012356789]|17[678]|18[0-9]|14[57])[0-9]{8}' )
phone_re = re . compile ( r '(\d+-\d+|\d+)' )
class JsonPipeline ( object ) :
def __init__ ( self ) :
self . file = open ( '/Users/wupeiqi/PycharmProjects/beauty/beauty/jieyicai.json' , 'wb' )
def process_item ( self , item , spider ) :
line = "%s %s\n" % ( item [ 'company' ] [ 0 ] . encode ( 'utf-8' ) , item [ 'title' ] [ 0 ] . encode ( 'utf-8' ) )
self . file . write ( line )
return item
class DBPipeline ( object ) :
def __init__ ( self ) :
self . db_pool = adbapi . ConnectionPool ( 'MySQLdb' ,
db = 'DbCenter' ,
user = 'root' ,
passwd = '123' ,
cursorclass = MySQLdb . cursors . DictCursor ,
use_unicode = True )
def process_item ( self , item , spider ) :
query = self . db_pool . runInteraction ( self . _conditional_insert , item )
query . addErrback ( self . handle_error )
return item
def _conditional_insert ( self , tx , item ) :
tx . execute ( "select nid from company where company = %s" , ( item [ 'company' ] [ 0 ] , ) )
result = tx . fetchone ( )
if result :
pass
else :
phone_obj = phone_re . search ( item [ 'info' ] [ 0 ] . strip ( ) )
phone = phone_obj . group ( ) if phone_obj else ' '
mobile_obj = mobile_re . search ( item [ 'info' ] [ 1 ] . strip ( ) )
mobile = mobile_obj . group ( ) if mobile_obj else ' '
values = (
item [ 'company' ] [ 0 ] ,
item [ 'qq' ] [ 0 ] ,
phone ,
mobile ,
item [ 'info' ] [ 2 ] . strip ( ) ,
item [ 'more' ] [ 0 ] )
tx . execute ( "insert into company(company,qq,phone,mobile,address,more) values(%s,%s,%s,%s,%s,%s)" , values )
def handle_error ( self , e ) :
print 'error' , e
pipelines
pipelines
上述代码中多个类的目的是,可以同时保存在文件和数据库中,保存的优先级可以在配置文件settings中定义。
ITEM_PIPELINES = {
'beauty.pipelines.DBPipeline' : 300 ,
'beauty.pipelines.JsonPipeline' : 100 ,
}
# 每行后面的整型值,确定了他们运行的顺序,item按数字从低到高的顺序,通过pipeline,通常将这些数字定义在0-1000范围内。