爬虫框架scrapy
Scrapy是一个为了爬取网站数据，提取结构性数据而编写的应用框架。 其可以应用在数据挖掘，信息处理或存储历史数据等一系列的程序中。
其最初是为了页面抓取 (更确切来说, 网络抓取 )所设计的， 也可以应用在获取API所返回的数据(例如 Amazon Associates Web Services ) 或者通用的网络爬虫。Scrapy用途广泛，可以用于数据挖掘、监测和自动化测试。
Scrapy 使用了 Twisted异步网络库来处理网络通讯。整体架构大致如下
Scrapy主要包括了以下组件：
- 引擎(Scrapy)
用来处理整个系统的数据流处理, 触发事务(框架核心) - 调度器(Scheduler)
用来接受引擎发过来的请求, 压入队列中, 并在引擎再次请求的时候返回. 可以想像成一个URL（抓取网页的网址或者说是链接）的优先队列, 由它来决定下一个要抓取的网址是什么, 同时去除重复的网址 - 下载器(Downloader)
用于下载网页内容, 并将网页内容返回给蜘蛛(Scrapy下载器是建立在twisted这个高效的异步模型上的) - 爬虫(Spiders)
爬虫是主要干活的, 用于从特定的网页中提取自己需要的信息, 即所谓的实体(Item)。用户也可以从中提取出链接,让Scrapy继续抓取下一个页面 - 项目管道(Pipeline)
负责处理爬虫从网页中抽取的实体，主要的功能是持久化实体、验证实体的有效性、清除不需要的信息。当页面被爬虫解析后，将被发送到项目管道，并经过几个特定的次序处理数据。 - 下载器中间件(Downloader Middlewares)
位于Scrapy引擎和下载器之间的框架，主要是处理Scrapy引擎与下载器之间的请求及响应。 - 爬虫中间件(Spider Middlewares)
介于Scrapy引擎和爬虫之间的框架，主要工作是处理蜘蛛的响应输入和请求输出。 - 调度中间件(Scheduler Middewares)
介于Scrapy引擎和调度之间的中间件，从Scrapy引擎发送到调度的请求和响应。
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
linux安装
| 1 |
|
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/
windows安装
a. pip3 install wheel
b. 下载twisted http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted
c. 进入下载目录，执行 pip3 install Twisted‑17.1.0‑cp35‑cp35m‑win_amd64.whl
d. pip3 install scrapy
e.pip3 install pypiwin32
二、基本使用
基本命令
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 |
|
1、创建项目
运行命令:
| 1 |
|
自动创建目录：
| 1 2 3 4 5 6 7 8 9 |
|
文件说明：
- 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
2、编写爬虫
在spiders目录中新建 xiaohuar_spider.py 文件
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 |
|
报错处理办法
import sys,os
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')3、运行
进入project_name目录，运行命令
| 1 |
|
4、递归的访问
以上的爬虫仅仅是爬去初始页，而我们爬虫是需要源源不断的执行下去，直到所有的网页被执行完毕
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
|
以上代码将符合规则的页面中的图片保存在指定目录，并且在HTML源码中找到所有的其他 a 标签的href属性，从而“递归”的执行下去，直到所有的页面都被访问过为止。以上代码之所以可以进行“递归”的访问相关URL，关键在于parse方法使用了 yield Request对象。
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
from scrapy.selector import Selector
from scrapy.http import HtmlResponse
html = """
first item
first item
second item
"""
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)
#!/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\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) def parse(self, response):
from scrapy.http.cookies import CookieJar
cookieJar = CookieJar()
cookieJar.extract_cookies(response, response.request)
print(cookieJar._cookies)更多选择器规则：http://scrapy-chs.readthedocs.io/zh_CN/latest/topics/selectors.html
5、格式化处理
上述实例只是简单的图片处理，所以在parse方法中直接处理。如果对于想要获取更多的数据（获取页面的价格、商品名称、QQ等），则可以利用Scrapy的items将数据格式化，然后统一交由pipelines来处理。
在items.py中创建类：
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 |
|
上述定义模板，以后对于从请求的源码中获取的数据同意按照此结构来获取，所以在spider中需要有一下操作：
#!/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\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) 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上述中的pipelines中有多个类，到底Scapy会自动执行那个？哈哈哈哈，当然需要先配置了，不然Scapy就蒙逼了。。。
在settings.py中做如下配置：
| 1 2 3 4 5 |
|
6. 小试牛刀
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
|
执行此爬虫文件，则在终端进入项目目录执行如下命令：
| 1 |
|
对于上述代码重要之处在于：
- Request是一个封装用户请求的类，在回调函数中yield该对象表示继续访问
- HtmlXpathSelector用于结构化HTML代码并提供选择器功能
7. 选择器
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
|
# -*- coding: utf-8 -*-
import scrapy
from scrapy.selector import HtmlXPathSelector
from scrapy.http.request import Request
from scrapy.http.cookies import CookieJar
from scrapy import FormRequest
class ChouTiSpider(scrapy.Spider):
# 爬虫应用的名称，通过此名称启动爬虫命令
name = "chouti"
# 允许的域名
allowed_domains = ["chouti.com"]
cookie_dict = {}
has_request_set = {}
def start_requests(self):
url = 'http://dig.chouti.com/'
# return [Request(url=url, callback=self.login)]
yield Request(url=url, callback=self.login)
def login(self, response):
cookie_jar = CookieJar()
cookie_jar.extract_cookies(response, response.request)
for k, v in cookie_jar._cookies.items():
for i, j in v.items():
for m, n in j.items():
self.cookie_dict[m] = n.value
req = Request(
url='http://dig.chouti.com/login',
method='POST',
headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
body='phone=8615131255089&password=pppppppp&oneMonth=1',
cookies=self.cookie_dict,
callback=self.check_login
)
yield req
def check_login(self, response):
req = Request(
url='http://dig.chouti.com/',
method='GET',
callback=self.show,
cookies=self.cookie_dict,
dont_filter=True
)
yield req
def show(self, response):
# print(response)
hxs = HtmlXPathSelector(response)
news_list = hxs.select('//div[@id="content-list"]/div[@class="item"]')
for new in news_list:
# temp = new.xpath('div/div[@class="part2"]/@share-linkid').extract()
link_id = new.xpath('*/div[@class="part2"]/@share-linkid').extract_first()
yield Request(
url='http://dig.chouti.com/link/vote?linksId=%s' %(link_id,),
method='POST',
cookies=self.cookie_dict,
callback=self.do_favor
)
page_list = hxs.select('//div[@id="dig_lcpage"]//a[re:test(@href, "/all/hot/recent/\d+")]/@href').extract()
for page in page_list:
page_url = 'http://dig.chouti.com%s' % page
import hashlib
hash = hashlib.md5()
hash.update(bytes(page_url,encoding='utf-8'))
key = hash.hexdigest()
if key in self.has_request_set:
pass
else:
self.has_request_set[key] = page_url
yield Request(
url=page_url,
method='GET',
callback=self.show
)
def do_favor(self, response):
print(response.text)# -*- coding: utf-8 -*-
import scrapy
from scrapy.http.response.html import HtmlResponse
from scrapy.http import Request
from scrapy.http.cookies import CookieJar
class ChoutiSpider(scrapy.Spider):
name = "chouti"
allowed_domains = ["chouti.com"]
start_urls = (
'http://www.chouti.com/',
)
def start_requests(self):
url = 'http://dig.chouti.com/'
yield Request(url=url, callback=self.login, meta={'cookiejar': True})
def login(self, response):
print(response.headers.getlist('Set-Cookie'))
req = Request(
url='http://dig.chouti.com/login',
method='POST',
headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
body='phone=8613121758648&password=woshiniba&oneMonth=1',
callback=self.check_login,
meta={'cookiejar': True}
)
yield req
def check_login(self, response):
print(response.text)注意：settings.py中设置DEPTH_LIMIT = 1来指定“递归”的层数。
8.中间件
class SpiderMiddleware(object):
def process_spider_input(self,response, spider):
"""
下载完成，执行，然后交给parse处理
:param response:
:param spider:
:return:
"""
pass
def process_spider_output(self,response, result, spider):
"""
spider处理完成，返回时调用
:param response:
:param result:
:param spider:
:return: 必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
"""
return result
def process_spider_exception(self,response, exception, spider):
"""
异常调用
:param response:
:param exception:
:param spider:
:return: None,继续交给后续中间件处理异常；含 Response 或 Item 的可迭代对象(iterable)，交给调度器或pipeline
"""
return None
def process_start_requests(self,start_requests, spider):
"""
爬虫启动时调用
:param start_requests:
:param spider:
:return: 包含 Request 对象的可迭代对象
"""
return start_requestsclass DownMiddleware1(object):
def process_request(self, request, spider):
"""
请求需要被下载时，经过所有下载器中间件的process_request调用
:param request:
:param spider:
:return:
None,继续后续中间件去下载；
Response对象，停止process_request的执行，开始执行process_response
Request对象，停止中间件的执行，将Request重新调度器
raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
"""
pass
def process_response(self, request, response, spider):
"""
spider处理完成，返回时调用
:param response:
:param result:
:param spider:
:return:
Response 对象：转交给其他中间件process_response
Request 对象：停止中间件，request会被重新调度下载
raise IgnoreRequest 异常：调用Request.errback
"""
print('response1')
return response
def process_exception(self, request, exception, spider):
"""
当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
:param response:
:param exception:
:param spider:
:return:
None：继续交给后续中间件处理异常；
Response对象：停止后续process_exception方法
Request对象：停止中间件，request将会被重新调用下载
"""
return None9. 自定制命令
- 在spiders同级创建任意目录，如：commands
- 在其中创建 crawlall.py 文件 （此处文件名就是自定义的命令）
from scrapy.commands import ScrapyCommand from scrapy.utils.project import get_project_settings class Command(ScrapyCommand): requires_project = True def syntax(self): return '[options]' def short_desc(self): return 'Runs all of the spiders' def run(self, args, opts): spider_list = self.crawler_process.spiders.list() for name in spider_list: self.crawler_process.crawl(name, **opts.__dict__) self.crawler_process.start() - 在settings.py 中添加配置 COMMANDS_MODULE = '项目名称.目录名称'
- 在项目目录执行命令：scrapy crawlall
import sys
from scrapy.cmdline import execute
if __name__ == '__main__':
execute(["scrapy","github","--nolog"])10. 自定义扩展
自定义扩展时，利用信号在指定位置注册制定操作
from scrapy import signals
class MyExtension(object):
def __init__(self, value):
self.value = value
@classmethod
def from_crawler(cls, crawler):
val = crawler.settings.getint('MMMM')
ext = cls(val)
crawler.signals.connect(ext.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(ext.spider_closed, signal=signals.spider_closed)
return ext
def spider_opened(self, spider):
print('open')
def spider_closed(self, spider):
print('close')11. 避免重复访问
scrapy默认使用 scrapy.dupefilter.RFPDupeFilter 进行去重，相关配置有：
| 1 2 3 |
|
class RepeatUrl:
def __init__(self):
self.visited_url = set()
@classmethod
def from_settings(cls, settings):
"""
初始化时，调用
:param settings:
:return:
"""
return cls()
def request_seen(self, request):
"""
检测当前请求是否已经被访问过
:param request:
:return: True表示已经访问过；False表示未访问过
"""
if request.url in self.visited_url:
return True
self.visited_url.add(request.url)
return False
def open(self):
"""
开始爬去请求时，调用
:return:
"""
print('open replication')
def close(self, reason):
"""
结束爬虫爬取时，调用
:param reason:
:return:
"""
print('close replication')
def log(self, request, spider):
"""
记录日志
:param request:
:param spider:
:return:
"""
print('repeat', request.url)12.其他
# -*- coding: utf-8 -*-
# Scrapy settings for step8_king project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
# 1. 爬虫名称
BOT_NAME = 'step8_king'
# 2. 爬虫应用路径
SPIDER_MODULES = ['step8_king.spiders']
NEWSPIDER_MODULE = 'step8_king.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# 3. 客户端 user-agent请求头
# USER_AGENT = 'step8_king (+http://www.yourdomain.com)'
# Obey robots.txt rules
# 4. 禁止爬虫配置
# ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
# 5. 并发请求数
# CONCURRENT_REQUESTS = 4
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# 6. 延迟下载秒数
# DOWNLOAD_DELAY = 2
# The download delay setting will honor only one of:
# 7. 单域名访问并发数，并且延迟下次秒数也应用在每个域名
# CONCURRENT_REQUESTS_PER_DOMAIN = 2
# 单IP访问并发数，如果有值则忽略：CONCURRENT_REQUESTS_PER_DOMAIN，并且延迟下次秒数也应用在每个IP
# CONCURRENT_REQUESTS_PER_IP = 3
# Disable cookies (enabled by default)
# 8. 是否支持cookie，cookiejar进行操作cookie
# COOKIES_ENABLED = True
# COOKIES_DEBUG = True
# Disable Telnet Console (enabled by default)
# 9. Telnet用于查看当前爬虫的信息，操作爬虫等...
# 使用telnet ip port ，然后通过命令操作
# TELNETCONSOLE_ENABLED = True
# TELNETCONSOLE_HOST = '127.0.0.1'
# TELNETCONSOLE_PORT = [6023,]
# 10. 默认请求头
# 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',
# }
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
# 11. 定义pipeline处理请求
# ITEM_PIPELINES = {
# 'step8_king.pipelines.JsonPipeline': 700,
# 'step8_king.pipelines.FilePipeline': 500,
# }
# 12. 自定义扩展，基于信号进行调用
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
# # 'step8_king.extensions.MyExtension': 500,
# }
# 13. 爬虫允许的最大深度，可以通过meta查看当前深度；0表示无深度
# DEPTH_LIMIT = 3
# 14. 爬取时，0表示深度优先Lifo(默认)；1表示广度优先FiFo
# 后进先出，深度优先
# DEPTH_PRIORITY = 0
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleLifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.LifoMemoryQueue'
# 先进先出，广度优先
# DEPTH_PRIORITY = 1
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleFifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.FifoMemoryQueue'
# 15. 调度器队列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'
# from scrapy.core.scheduler import Scheduler
# 16. 访问URL去重
# DUPEFILTER_CLASS = 'step8_king.duplication.RepeatUrl'
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
"""
17. 自动限速算法
from scrapy.contrib.throttle import AutoThrottle
自动限速设置
1. 获取最小延迟 DOWNLOAD_DELAY
2. 获取最大延迟 AUTOTHROTTLE_MAX_DELAY
3. 设置初始下载延迟 AUTOTHROTTLE_START_DELAY
4. 当请求下载完成后，获取其"连接"时间 latency，即：请求连接到接受到响应头之间的时间
5. 用于计算的... AUTOTHROTTLE_TARGET_CONCURRENCY
target_delay = latency / self.target_concurrency
new_delay = (slot.delay + target_delay) / 2.0 # 表示上一次的延迟时间
new_delay = max(target_delay, new_delay)
new_delay = min(max(self.mindelay, new_delay), self.maxdelay)
slot.delay = new_delay
"""
# 开始自动限速
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# 初始下载延迟
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# 最大下载延迟
# AUTOTHROTTLE_MAX_DELAY = 10
# The average number of requests Scrapy should be sending in parallel to each remote server
# 平均每秒并发数
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
# 是否显示
# AUTOTHROTTLE_DEBUG = True
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
"""
18. 启用缓存
目的用于将已经发送的请求或相应缓存下来，以便以后使用
from scrapy.downloadermiddlewares.httpcache import HttpCacheMiddleware
from scrapy.extensions.httpcache import DummyPolicy
from scrapy.extensions.httpcache import FilesystemCacheStorage
"""
# 是否启用缓存策略
# HTTPCACHE_ENABLED = True
# 缓存策略：所有请求均缓存，下次在请求直接访问原来的缓存即可
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.DummyPolicy"
# 缓存策略：根据Http响应头：Cache-Control、Last-Modified 等进行缓存的策略
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"
# 缓存超时时间
# HTTPCACHE_EXPIRATION_SECS = 0
# 缓存保存路径
# HTTPCACHE_DIR = 'httpcache'
# 缓存忽略的Http状态码
# HTTPCACHE_IGNORE_HTTP_CODES = []
# 缓存存储的插件
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
"""
19. 代理，需要在环境变量中设置
from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
方式一：使用默认
os.environ
{
http_proxy:http://root:[email protected]:9999/
https_proxy:http://192.168.11.11:9999/
}
方式二：使用自定义下载中间件
def to_bytes(text, encoding=None, errors='strict'):
if isinstance(text, bytes):
return text
if not isinstance(text, six.string_types):
raise TypeError('to_bytes must receive a unicode, str or bytes '
'object, got %s' % type(text).__name__)
if encoding is None:
encoding = 'utf-8'
return text.encode(encoding, errors)
class ProxyMiddleware(object):
def process_request(self, request, spider):
PROXIES = [
{'ip_port': '111.11.228.75:80', 'user_pass': ''},
{'ip_port': '120.198.243.22:80', 'user_pass': ''},
{'ip_port': '111.8.60.9:8123', 'user_pass': ''},
{'ip_port': '101.71.27.120:80', 'user_pass': ''},
{'ip_port': '122.96.59.104:80', 'user_pass': ''},
{'ip_port': '122.224.249.122:8088', 'user_pass': ''},
]
proxy = random.choice(PROXIES)
if proxy['user_pass'] is not None:
request.meta['proxy'] = to_bytes（"http://%s" % proxy['ip_port']）
encoded_user_pass = base64.encodestring(to_bytes(proxy['user_pass']))
request.headers['Proxy-Authorization'] = to_bytes('Basic ' + encoded_user_pass)
print "**************ProxyMiddleware have pass************" + proxy['ip_port']
else:
print "**************ProxyMiddleware no pass************" + proxy['ip_port']
request.meta['proxy'] = to_bytes("http://%s" % proxy['ip_port'])
DOWNLOADER_MIDDLEWARES = {
'step8_king.middlewares.ProxyMiddleware': 500,
}
"""
"""
20. Https访问
Https访问时有两种情况：
1. 要爬取网站使用的可信任证书(默认支持)
DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
DOWNLOADER_CLIENTCONTEXTFACTORY = "scrapy.core.downloader.contextfactory.ScrapyClientContextFactory"
2. 要爬取网站使用的自定义证书
DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
DOWNLOADER_CLIENTCONTEXTFACTORY = "step8_king.https.MySSLFactory"
# https.py
from scrapy.core.downloader.contextfactory import ScrapyClientContextFactory
from twisted.internet.ssl import (optionsForClientTLS, CertificateOptions, PrivateCertificate)
class MySSLFactory(ScrapyClientContextFactory):
def getCertificateOptions(self):
from OpenSSL import crypto
v1 = crypto.load_privatekey(crypto.FILETYPE_PEM, open('/Users/wupeiqi/client.key.unsecure', mode='r').read())
v2 = crypto.load_certificate(crypto.FILETYPE_PEM, open('/Users/wupeiqi/client.pem', mode='r').read())
return CertificateOptions(
privateKey=v1, # pKey对象
certificate=v2, # X509对象
verify=False,
method=getattr(self, 'method', getattr(self, '_ssl_method', None))
)
其他：
相关类
scrapy.core.downloader.handlers.http.HttpDownloadHandler
scrapy.core.downloader.webclient.ScrapyHTTPClientFactory
scrapy.core.downloader.contextfactory.ScrapyClientContextFactory
相关配置
DOWNLOADER_HTTPCLIENTFACTORY
DOWNLOADER_CLIENTCONTEXTFACTORY
"""
"""
21. 爬虫中间件
class SpiderMiddleware(object):
def process_spider_input(self,response, spider):
'''
下载完成，执行，然后交给parse处理
:param response:
:param spider:
:return:
'''
pass
def process_spider_output(self,response, result, spider):
'''
spider处理完成，返回时调用
:param response:
:param result:
:param spider:
:return: 必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
'''
return result
def process_spider_exception(self,response, exception, spider):
'''
异常调用
:param response:
:param exception:
:param spider:
:return: None,继续交给后续中间件处理异常；含 Response 或 Item 的可迭代对象(iterable)，交给调度器或pipeline
'''
return None
def process_start_requests(self,start_requests, spider):
'''
爬虫启动时调用
:param start_requests:
:param spider:
:return: 包含 Request 对象的可迭代对象
'''
return start_requests
内置爬虫中间件：
'scrapy.contrib.spidermiddleware.httperror.HttpErrorMiddleware': 50,
'scrapy.contrib.spidermiddleware.offsite.OffsiteMiddleware': 500,
'scrapy.contrib.spidermiddleware.referer.RefererMiddleware': 700,
'scrapy.contrib.spidermiddleware.urllength.UrlLengthMiddleware': 800,
'scrapy.contrib.spidermiddleware.depth.DepthMiddleware': 900,
"""
# from scrapy.contrib.spidermiddleware.referer import RefererMiddleware
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
# 'step8_king.middlewares.SpiderMiddleware': 543,
}
"""
22. 下载中间件
class DownMiddleware1(object):
def process_request(self, request, spider):
'''
请求需要被下载时，经过所有下载器中间件的process_request调用
:param request:
:param spider:
:return:
None,继续后续中间件去下载；
Response对象，停止process_request的执行，开始执行process_response
Request对象，停止中间件的执行，将Request重新调度器
raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
'''
pass
def process_response(self, request, response, spider):
'''
spider处理完成，返回时调用
:param response:
:param result:
:param spider:
:return:
Response 对象：转交给其他中间件process_response
Request 对象：停止中间件，request会被重新调度下载
raise IgnoreRequest 异常：调用Request.errback
'''
print('response1')
return response
def process_exception(self, request, exception, spider):
'''
当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
:param response:
:param exception:
:param spider:
:return:
None：继续交给后续中间件处理异常；
Response对象：停止后续process_exception方法
Request对象：停止中间件，request将会被重新调用下载
'''
return None
默认下载中间件
{
'scrapy.contrib.downloadermiddleware.robotstxt.RobotsTxtMiddleware': 100,
'scrapy.contrib.downloadermiddleware.httpauth.HttpAuthMiddleware': 300,
'scrapy.contrib.downloadermiddleware.downloadtimeout.DownloadTimeoutMiddleware': 350,
'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': 400,
'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': 500,
'scrapy.contrib.downloadermiddleware.defaultheaders.DefaultHeadersMiddleware': 550,
'scrapy.contrib.downloadermiddleware.redirect.MetaRefreshMiddleware': 580,
'scrapy.contrib.downloadermiddleware.httpcompression.HttpCompressionMiddleware': 590,
'scrapy.contrib.downloadermiddleware.redirect.RedirectMiddleware': 600,
'scrapy.contrib.downloadermiddleware.cookies.CookiesMiddleware': 700,
'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 750,
'scrapy.contrib.downloadermiddleware.chunked.ChunkedTransferMiddleware': 830,
'scrapy.contrib.downloadermiddleware.stats.DownloaderStats': 850,
'scrapy.contrib.downloadermiddleware.httpcache.HttpCacheMiddleware': 900,
}
"""
# from scrapy.contrib.downloadermiddleware.httpauth import HttpAuthMiddleware
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# 'step8_king.middlewares.DownMiddleware1': 100,
# 'step8_king.middlewares.DownMiddleware2': 500,
# }13. 大文件下载
示例文件：猛击下载
14.TinyScrapy
from twisted.web.client import getPage
from twisted.internet import reactor
from twisted.internet import defer
url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
def callback(arg):
print('回来一个', arg)
defer_list = []
for url in url_list:
ret = getPage(bytes(url, encoding='utf8'))
ret.addCallback(callback)
defer_list.append(ret)
def stop(arg):
print('已经全部现在完毕', arg)
reactor.stop()
d = defer.DeferredList(defer_list)
d.addBoth(stop)
reactor.run()#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.web.client import getPage
from twisted.internet import reactor
from twisted.internet import defer
@defer.inlineCallbacks
def task(url):
ret = getPage(bytes(url, encoding='utf8'))
ret.addCallback(callback)
yield ret
def callback(arg):
print('回来一个', arg)
url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
defer_list = []
for url in url_list:
ret = task(url)
defer_list.append(ret)
def stop(arg):
print('已经全部现在完毕', arg)
reactor.stop()
d = defer.DeferredList(defer_list)
d.addBoth(stop)
reactor.run()#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.internet import defer
from twisted.web.client import getPage
from twisted.internet import reactor
import threading
def _next_request():
_next_request_from_scheduler()
def _next_request_from_scheduler():
ret = getPage(bytes('http://www.chouti.com', encoding='utf8'))
ret.addCallback(callback)
ret.addCallback(lambda _: reactor.callLater(0, _next_request))
_closewait = None
@defer.inlineCallbacks
def engine_start():
global _closewait
_closewait = defer.Deferred()
yield _closewait
@defer.inlineCallbacks
def task(url):
reactor.callLater(0, _next_request)
yield engine_start()
counter = 0
def callback(arg):
global counter
counter +=1
if counter == 10:
_closewait.callback(None)
print('one', len(arg))
def stop(arg):
print('all done', arg)
reactor.stop()
if __name__ == '__main__':
url = 'http://www.cnblogs.com'
defer_list = []
deferObj = task(url)
defer_list.append(deferObj)
v = defer.DeferredList(defer_list)
v.addBoth(stop)
reactor.run()#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.web.client import getPage, defer
from twisted.internet import reactor
import queue
class Response(object):
def __init__(self, body, request):
self.body = body
self.request = request
self.url = request.url
@property
def text(self):
return self.body.decode('utf-8')
class Request(object):
def __init__(self, url, callback=None):
self.url = url
self.callback = callback
class Scheduler(object):
def __init__(self, engine):
self.q = queue.Queue()
self.engine = engine
def enqueue_request(self, request):
self.q.put(request)
def next_request(self):
try:
req = self.q.get(block=False)
except Exception as e:
req = None
return req
def size(self):
return self.q.qsize()
class ExecutionEngine(object):
def __init__(self):
self._closewait = None
self.running = True
self.start_requests = None
self.scheduler = Scheduler(self)
self.inprogress = set()
def check_empty(self, response):
if not self.running:
self._closewait.callback('......')
def _next_request(self):
while self.start_requests:
try:
request = next(self.start_requests)
except StopIteration:
self.start_requests = None
else:
self.scheduler.enqueue_request(request)
while len(self.inprogress) < 5 and self.scheduler.size() > 0: # 最大并发数为5
request = self.scheduler.next_request()
if not request:
break
self.inprogress.add(request)
d = getPage(bytes(request.url, encoding='utf-8'))
d.addBoth(self._handle_downloader_output, request)
d.addBoth(lambda x, req: self.inprogress.remove(req), request)
d.addBoth(lambda x: self._next_request())
if len(self.inprogress) == 0 and self.scheduler.size() == 0:
self._closewait.callback(None)
def _handle_downloader_output(self, body, request):
"""
获取内容，执行回调函数，并且把回调函数中的返回值获取，并添加到队列中
:param response:
:param request:
:return:
"""
import types
response = Response(body, request)
func = request.callback or self.spider.parse
gen = func(response)
if isinstance(gen, types.GeneratorType):
for req in gen:
self.scheduler.enqueue_request(req)
@defer.inlineCallbacks
def start(self):
self._closewait = defer.Deferred()
yield self._closewait
def open_spider(self, spider, start_requests):
self.start_requests = start_requests
self.spider = spider
reactor.callLater(0, self._next_request)
class Crawler(object):
def __init__(self, spidercls):
self.spidercls = spidercls
self.spider = None
self.engine = None
@defer.inlineCallbacks
def crawl(self):
self.engine = ExecutionEngine()
self.spider = self.spidercls()
start_requests = iter(self.spider.start_requests())
start_requests = iter(start_requests)
self.engine.open_spider(self.spider, start_requests)
yield self.engine.start()
class CrawlerProcess(object):
def __init__(self):
self._active = set()
self.crawlers = set()
def crawl(self, spidercls, *args, **kwargs):
crawler = Crawler(spidercls)
self.crawlers.add(crawler)
d = crawler.crawl(*args, **kwargs)
self._active.add(d)
return d
def start(self):
dl = defer.DeferredList(self._active)
dl.addBoth(self._stop_reactor)
reactor.run()
def _stop_reactor(self, _=None):
reactor.stop()
class Spider(object):
def start_requests(self):
for url in self.start_urls:
yield Request(url)
class ChoutiSpider(Spider):
name = "chouti"
start_urls = [
'http://dig.chouti.com/',
]
def parse(self, response):
print(response.text)
class CnblogsSpider(Spider):
name = "cnblogs"
start_urls = [
'http://www.cnblogs.com/',
]
def parse(self, response):
print(response.text)
if __name__ == '__main__':
spider_cls_list = [ChoutiSpider, CnblogsSpider]
crawler_process = CrawlerProcess()
for spider_cls in spider_cls_list:
crawler_process.crawl(spider_cls)
crawler_process.start()#!/usr/bin/env python
# -*- coding:utf-8 -*-
import types
from twisted.internet import defer
from twisted.web.client import getPage
from twisted.internet import reactor
class Request(object):
def __init__(self, url, callback):
self.url = url
self.callback = callback
self.priority = 0
class HttpResponse(object):
def __init__(self, content, request):
self.content = content
self.request = request
class ChouTiSpider(object):
def start_requests(self):
url_list = ['http://www.cnblogs.com/', 'http://www.bing.com']
for url in url_list:
yield Request(url=url, callback=self.parse)
def parse(self, response):
print(response.request.url)
# yield Request(url="http://www.baidu.com", callback=self.parse)
from queue import Queue
Q = Queue()
class CallLaterOnce(object):
def __init__(self, func, *a, **kw):
self._func = func
self._a = a
self._kw = kw
self._call = None
def schedule(self, delay=0):
if self._call is None:
self._call = reactor.callLater(delay, self)
def cancel(self):
if self._call:
self._call.cancel()
def __call__(self):
self._call = None
return self._func(*self._a, **self._kw)
class Engine(object):
def __init__(self):
self.nextcall = None
self.crawlling = []
self.max = 5
self._closewait = None
def get_response(self,content, request):
response = HttpResponse(content, request)
gen = request.callback(response)
if isinstance(gen, types.GeneratorType):
for req in gen:
req.priority = request.priority + 1
Q.put(req)
def rm_crawlling(self,response,d):
self.crawlling.remove(d)
def _next_request(self,spider):
if Q.qsize() == 0 and len(self.crawlling) == 0:
self._closewait.callback(None)
if len(self.crawlling) >= 5:
return
while len(self.crawlling) < 5:
try:
req = Q.get(block=False)
except Exception as e:
req = None
if not req:
return
d = getPage(req.url.encode('utf-8'))
self.crawlling.append(d)
d.addCallback(self.get_response, req)
d.addCallback(self.rm_crawlling,d)
d.addCallback(lambda _: self.nextcall.schedule())
@defer.inlineCallbacks
def crawl(self):
spider = ChouTiSpider()
start_requests = iter(spider.start_requests())
flag = True
while flag:
try:
req = next(start_requests)
Q.put(req)
except StopIteration as e:
flag = False
self.nextcall = CallLaterOnce(self._next_request,spider)
self.nextcall.schedule()
self._closewait = defer.Deferred()
yield self._closewait
@defer.inlineCallbacks
def pp(self):
yield self.crawl()
_active = set()
obj = Engine()
d = obj.crawl()
_active.add(d)
li = defer.DeferredList(_active)
li.addBoth(lambda _,*a,**kw: reactor.stop())
reactor.run()
http://www.cnblogs.com/wupeiqi/articles/6229292.html
http://www.cnblogs.com/wupeiqi/articles/5354900.html
https://www.cnblogs.com/wupeiqi/articles/6912807.html
https://www.cnblogs.com/wupeiqi/articles/6698151.html
https://www.cnblogs.com/hyit/category/1117750.html
更多请参见Scrapy文档：http://scrapy-chs.readthedocs.io/zh_CN/latest/index.html