python爬蟲Scrapy及其性能相關

爬蟲性能相關

 

 

在編寫爬蟲時，性能的消耗主要在IO請求中，當單進程單線程模式下請求URL時必然會引發等待，從而使得請求總體變慢。

 1 import requests
 2 
 3 def fetch_async(url):
 4     response = requests.get(url)
 5     return response
 6 
 7 
 8 url_list = ['http://www.github.com', 'http://www.bing.com']
 9 
10 for url in url_list:
11     fetch_async(url)
12 
13 1.同步執行

同步執行

 1 from concurrent.futures import ThreadPoolExecutor
 2 import requests
 3 
 4 
 5 def fetch_async(url):
 6     response = requests.get(url)
 7     return response
 8 
 9 
10 url_list = ['http://www.github.com', 'http://www.bing.com']
11 pool = ThreadPoolExecutor(5)
12 for url in url_list:
13     pool.submit(fetch_async, url)
14 pool.shutdown(wait=True)

多線程執行

 1 from concurrent.futures import ThreadPoolExecutor
 2 import requests
 3 
 4 def fetch_async(url):
 5     response = requests.get(url)
 6     return response
 7 
 8 
 9 def callback(future):
10     print(future.result())
11 
12 
13 url_list = ['http://www.github.com', 'http://www.bing.com']
14 pool = ThreadPoolExecutor(5)
15 for url in url_list:
16     v = pool.submit(fetch_async, url)
17     v.add_done_callback(callback)
18 pool.shutdown(wait=True)

多線程+回調函數執行

 1 from concurrent.futures import ProcessPoolExecutor
 2 import requests
 3 
 4 def fetch_async(url):
 5     response = requests.get(url)
 6     return response
 7 
 8 
 9 url_list = ['http://www.github.com', 'http://www.bing.com']
10 pool = ProcessPoolExecutor(5)
11 for url in url_list:
12     pool.submit(fetch_async, url)
13 pool.shutdown(wait=True)

多進程執行

from concurrent.futures import ProcessPoolExecutor
import requests


def fetch_async(url):
    response = requests.get(url)
    return response


def callback(future):
    print(future.result())


url_list = ['http://www.github.com', 'http://www.bing.com']
pool = ProcessPoolExecutor(5)
for url in url_list:
    v = pool.submit(fetch_async, url)
    v.add_done_callback(callback)
pool.shutdown(wait=True)

多進程+回調函數執行

經過上述代碼都可以完成對請求性能的提升，對於多線程和多進行的缺點是在IO阻塞時會形成了線程和進程的浪費，因此異步IO回事首選：

import asyncio


@asyncio.coroutine
def func1():
    print('before...func1......')
    yield from asyncio.sleep(5)
    print('end...func1......')


tasks = [func1(), func1()]

loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.gather(*tasks))
loop.close()

1.asyncio示例1

import asyncio


@asyncio.coroutine
def fetch_async(host, url='/'):
    print(host, url)
    reader, writer = yield from asyncio.open_connection(host, 80)

    request_header_content = """GET %s HTTP/1.0\r\nHost: %s\r\n\r\n""" % (url, host,)
    request_header_content = bytes(request_header_content, encoding='utf-8')

    writer.write(request_header_content)
    yield from writer.drain()
    text = yield from reader.read()
    print(host, url, text)
    writer.close()

tasks = [
    fetch_async('www.cnblogs.com', '/wupeiqi/'),
    fetch_async('dig.chouti.com', '/pic/show?nid=4073644713430508&lid=10273091')
]

loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()

1.asyncio示例2

import aiohttp
import asyncio


@asyncio.coroutine
def fetch_async(url):
    print(url)
    response = yield from aiohttp.request('GET', url)
    # data = yield from response.read()
    # print(url, data)
    print(url, response)
    response.close()


tasks = [fetch_async('http://www.google.com/'), fetch_async('http://www.chouti.com/')]

event_loop = asyncio.get_event_loop()
results = event_loop.run_until_complete(asyncio.gather(*tasks))
event_loop.close()

2.asyncio + aiohttp

import asyncio
import requests


@asyncio.coroutine
def fetch_async(func, *args):
    loop = asyncio.get_event_loop()
    future = loop.run_in_executor(None, func, *args)
    response = yield from future
    print(response.url, response.content)


tasks = [
    fetch_async(requests.get, 'http://www.cnblogs.com/wupeiqi/'),
    fetch_async(requests.get, 'http://dig.chouti.com/pic/show?nid=4073644713430508&lid=10273091')
]

loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()

3.asyncio + requests

import gevent

import requests
from gevent import monkey

monkey.patch_all()


def fetch_async(method, url, req_kwargs):
    print(method, url, req_kwargs)
    response = requests.request(method=method, url=url, **req_kwargs)
    print(response.url, response.content)

# ##### 發送請求 #####
gevent.joinall([
    gevent.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={}),
    gevent.spawn(fetch_async, method='get', url='https://www.yahoo.com/', req_kwargs={}),
    gevent.spawn(fetch_async, method='get', url='https://github.com/', req_kwargs={}),
])

# ##### 發送請求（協程池控制最大協程數量） #####
# from gevent.pool import Pool
# pool = Pool(None)
# gevent.joinall([
#     pool.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={}),
#     pool.spawn(fetch_async, method='get', url='https://www.yahoo.com/', req_kwargs={}),
#     pool.spawn(fetch_async, method='get', url='https://www.github.com/', req_kwargs={}),
# ])

4.gevent + requests

import grequests


request_list = [
    grequests.get('http://httpbin.org/delay/1', timeout=0.001),
    grequests.get('http://fakedomain/'),
    grequests.get('http://httpbin.org/status/500')
]


# ##### 執行並獲取響應列表 #####
# response_list = grequests.map(request_list)
# print(response_list)


# ##### 執行並獲取響應列表（處理異常） #####
# def exception_handler(request, exception):
# print(request,exception)
#     print("Request failed")

# response_list = grequests.map(request_list, exception_handler=exception_handler)
# print(response_list)

5.grequests

 1 from twisted.web.client import getPage, defer
 2 from twisted.internet import reactor
 3 
 4 
 5 def all_done(arg):
 6     reactor.stop()
 7 
 8 
 9 def callback(contents):
10     print(contents)
11 
12 
13 deferred_list = []
14 
15 url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
16 for url in url_list:
17     deferred = getPage(bytes(url, encoding='utf8'))
18     deferred.addCallback(callback)
19     deferred_list.append(deferred)
20 
21 dlist = defer.DeferredList(deferred_list)
22 dlist.addBoth(all_done)
23 
24 reactor.run()

6.Twisted示例

 1 from tornado.httpclient import AsyncHTTPClient
 2 from tornado.httpclient import HTTPRequest
 3 from tornado import ioloop
 4 
 5 
 6 def handle_response(response):
 7     """
 8     處理返回值內容（須要維護計數器，來中止IO循環），調用 ioloop.IOLoop.current().stop()
 9     :param response: 
10     :return: 
11     """
12     if response.error:
13         print("Error:", response.error)
14     else:
15         print(response.body)
16 
17 
18 def func():
19     url_list = [
20         'http://www.baidu.com',
21         'http://www.bing.com',
22     ]
23     for url in url_list:
24         print(url)
25         http_client = AsyncHTTPClient()
26         http_client.fetch(HTTPRequest(url), handle_response)
27 
28 
29 ioloop.IOLoop.current().add_callback(func)
30 ioloop.IOLoop.current().start()

7.Tornado

 1 from twisted.internet import reactor
 2 from twisted.web.client import getPage
 3 import urllib.parse
 4 
 5 
 6 def one_done(arg):
 7     print(arg)
 8     reactor.stop()
 9 
10 post_data = urllib.parse.urlencode({'check_data': 'adf'})
11 post_data = bytes(post_data, encoding='utf8')
12 headers = {b'Content-Type': b'application/x-www-form-urlencoded'}
13 response = getPage(bytes('http://dig.chouti.com/login', encoding='utf8'),
14                    method=bytes('POST', encoding='utf8'),
15                    postdata=post_data,
16                    cookies={},
17                    headers=headers)
18 response.addBoth(one_done)
19 
20 reactor.run()

Twisted更多

以上均是Python內置以及第三方模塊提供異步IO請求模塊，使用簡便大大提升效率，而對於異步IO請求的本質則是【非阻塞Socket】+【IO多路複用】：

  1 import select
  2 import socket
  3 import time
  4 
  5 
  6 class AsyncTimeoutException(TimeoutError):
  7     """
  8     請求超時異常類
  9     """
 10 
 11     def __init__(self, msg):
 12         self.msg = msg
 13         super(AsyncTimeoutException, self).__init__(msg)
 14 
 15 
 16 class HttpContext(object):
 17     """封裝請求和相應的基本數據"""
 18 
 19     def __init__(self, sock, host, port, method, url, data, callback, timeout=5):
 20         """
 21         sock: 請求的客戶端socket對象
 22         host: 請求的主機名
 23         port: 請求的端口
 24         port: 請求的端口
 25         method: 請求方式
 26         url: 請求的URL
 27         data: 請求時請求體中的數據
 28         callback: 請求完成後的回調函數
 29         timeout: 請求的超時時間
 30         """
 31         self.sock = sock
 32         self.callback = callback
 33         self.host = host
 34         self.port = port
 35         self.method = method
 36         self.url = url
 37         self.data = data
 38 
 39         self.timeout = timeout
 40 
 41         self.__start_time = time.time()
 42         self.__buffer = []
 43 
 44     def is_timeout(self):
 45         """當前請求是否已經超時"""
 46         current_time = time.time()
 47         if (self.__start_time + self.timeout) < current_time:
 48             return True
 49 
 50     def fileno(self):
 51         """請求sockect對象的文件描述符，用於select監聽"""
 52         return self.sock.fileno()
 53 
 54     def write(self, data):
 55         """在buffer中寫入響應內容"""
 56         self.__buffer.append(data)
 57 
 58     def finish(self, exc=None):
 59         """在buffer中寫入響應內容完成，執行請求的回調函數"""
 60         if not exc:
 61             response = b''.join(self.__buffer)
 62             self.callback(self, response, exc)
 63         else:
 64             self.callback(self, None, exc)
 65 
 66     def send_request_data(self):
 67         content = """%s %s HTTP/1.0\r\nHost: %s\r\n\r\n%s""" % (
 68             self.method.upper(), self.url, self.host, self.data,)
 69 
 70         return content.encode(encoding='utf8')
 71 
 72 
 73 class AsyncRequest(object):
 74     def __init__(self):
 75         self.fds = []
 76         self.connections = []
 77 
 78     def add_request(self, host, port, method, url, data, callback, timeout):
 79         """建立一個要請求"""
 80         client = socket.socket()
 81         client.setblocking(False)
 82         try:
 83             client.connect((host, port))
 84         except BlockingIOError as e:
 85             pass
 86             # print('已經向遠程發送鏈接的請求')
 87         req = HttpContext(client, host, port, method, url, data, callback, timeout)
 88         self.connections.append(req)
 89         self.fds.append(req)
 90 
 91     def check_conn_timeout(self):
 92         """檢查全部的請求，是否有已經鏈接超時，若是有則終止"""
 93         timeout_list = []
 94         for context in self.connections:
 95             if context.is_timeout():
 96                 timeout_list.append(context)
 97         for context in timeout_list:
 98             context.finish(AsyncTimeoutException('請求超時'))
 99             self.fds.remove(context)
100             self.connections.remove(context)
101 
102     def running(self):
103         """事件循環，用於檢測請求的socket是否已經就緒，從而執行相關操做"""
104         while True:
105             r, w, e = select.select(self.fds, self.connections, self.fds, 0.05)
106 
107             if not self.fds:
108                 return
109 
110             for context in r:
111                 sock = context.sock
112                 while True:
113                     try:
114                         data = sock.recv(8096)
115                         if not data:
116                             self.fds.remove(context)
117                             context.finish()
118                             break
119                         else:
120                             context.write(data)
121                     except BlockingIOError as e:
122                         break
123                     except TimeoutError as e:
124                         self.fds.remove(context)
125                         self.connections.remove(context)
126                         context.finish(e)
127                         break
128 
129             for context in w:
130                 # 已經鏈接成功遠程服務器，開始向遠程發送請求數據
131                 if context in self.fds:
132                     data = context.send_request_data()
133                     context.sock.sendall(data)
134                     self.connections.remove(context)
135 
136             self.check_conn_timeout()
137 
138 
139 if __name__ == '__main__':
140     def callback_func(context, response, ex):
141         """
142         :param context: HttpContext對象，內部封裝了請求相關信息
143         :param response: 請求響應內容
144         :param ex: 是否出現異常（若是有異常則值爲異常對象；不然值爲None）
145         :return:
146         """
147         print(context, response, ex)
148 
149     obj = AsyncRequest()
150     url_list = [
151         {'host': 'www.google.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5,
152          'callback': callback_func},
153         {'host': 'www.baidu.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5,
154          'callback': callback_func},
155         {'host': 'www.bing.com', 'port': 80, 'method': 'GET', 'url': '/', 'data': '', 'timeout': 5,
156          'callback': callback_func},
157     ]
158     for item in url_list:
159         print(item)
160         obj.add_request(**item)
161 
162     obj.running()

史上最牛逼的異步IO模塊

 

Scrapy

 

 

Scrapy是一個爲了爬取網站數據，提取結構性數據而編寫的應用框架。 其能夠應用在數據挖掘，信息處理或存儲歷史數據等一系列的程序中。
其最初是爲了頁面抓取 (更確切來講, 網絡抓取 )所設計的， 也能夠應用在獲取API所返回的數據(例如 Amazon Associates Web Services ) 或者通用的網絡爬蟲。Scrapy用途普遍，能夠用於數據挖掘、監測和自動化測試。

Scrapy 使用了 Twisted異步網絡庫來處理網絡通信。總體架構大體以下

 

Scrapy主要包括瞭如下組件：

• 引擎(Scrapy)
  用來處理整個系統的數據流處理, 觸發事務(框架核心)
• 調度器(Scheduler)
  用來接受引擎發過來的請求, 壓入隊列中, 並在引擎再次請求的時候返回. 能夠想像成一個URL（抓取網頁的網址或者說是連接）的優先隊列, 由它來決定下一個要抓取的網址是什麼, 同時去除重複的網址
• 下載器(Downloader)
  用於下載網頁內容, 並將網頁內容返回給蜘蛛(Scrapy下載器是創建在twisted這個高效的異步模型上的)
• 爬蟲(Spiders)
  爬蟲是主要幹活的, 用於從特定的網頁中提取本身須要的信息, 即所謂的實體(Item)。用戶也能夠從中提取出連接,讓Scrapy繼續抓取下一個頁面
• 項目管道(Pipeline)
  負責處理爬蟲從網頁中抽取的實體，主要的功能是持久化實體、驗證明體的有效性、清除不須要的信息。當頁面被爬蟲解析後，將被髮送到項目管道，並通過幾個特定的次序處理數據。
• 下載器中間件(Downloader Middlewares)
  位於Scrapy引擎和下載器之間的框架，主要是處理Scrapy引擎與下載器之間的請求及響應。
• 爬蟲中間件(Spider Middlewares)
  介於Scrapy引擎和爬蟲之間的框架，主要工做是處理蜘蛛的響應輸入和請求輸出。
• 調度中間件(Scheduler Middewares)
  介於Scrapy引擎和調度之間的中間件，從Scrapy引擎發送到調度的請求和響應。

Scrapy運行流程大概以下：

1. 引擎從調度器中取出一個連接(URL)用於接下來的抓取
2. 引擎把URL封裝成一個請求(Request)傳給下載器
3. 下載器把資源下載下來，並封裝成應答包(Response)
4. 爬蟲解析Response
5. 解析出實體（Item）,則交給實體管道進行進一步的處理
6. 解析出的是連接（URL）,則把URL交給調度器等待抓取

 1、scrapy的安裝

Linux
      pip3 install scrapy
 
 
Windows
      a. pip3 install wheel
      b. 下載twisted http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted
      c. 進入下載目錄，執行 pip3 install Twisted‑17.1.0‑cp35‑cp35m‑win_amd64.whl
      d. pip3 install scrapy
      e. 下載並安裝pywin32：https://sourceforge.net/projects/pywin32/files/

2、scrapy的基本使用

一、基本命令

1. scrapy startproject 項目名稱
   - 在當前目錄中建立中建立一個項目文件（相似於Django）
 
2. scrapy genspider [-t template] <name> <domain>
   - 建立爬蟲應用
   如：
      scrapy gensipider -t basic oldboy oldboy.com
      scrapy gensipider -t xmlfeed autohome autohome.com.cn
   PS:
      查看全部命令：scrapy gensipider -l
      查看模板命令：scrapy gensipider -d 模板名稱
 
3. scrapy list
   - 展現爬蟲應用列表
 
4. scrapy crawl 爬蟲應用名稱
   - 運行單獨爬蟲應用

二、項目結構及其爬蟲應用簡介

project_name/
   scrapy.cfg
   project_name/
       __init__.py
       items.py
       pipelines.py
       settings.py
       spiders/
           __init__.py
           爬蟲1.py
           爬蟲2.py
           爬蟲3.py

文件說明：

• scrapy.cfg  項目的主配置信息。（真正爬蟲相關的配置信息在settings.py文件中）
• items.py    設置數據存儲模板，用於結構化數據，如：Django的Model
• pipelines    數據處理行爲，如：通常結構化的數據持久化
• settings.py 配置文件，如：遞歸的層數、併發數，延遲下載等
• spiders      爬蟲目錄，如：建立文件，編寫爬蟲規則

注意：通常建立爬蟲文件時，以網站域名命名

import scrapy
 
class XiaoHuarSpider(scrapy.spiders.Spider):
    name = "xiaohuar"                            # 爬蟲名稱 *****
    allowed_domains = ["xiaohuar.com"]  # 容許的域名
    start_urls = [
        "http://www.xiaohuar.com/hua/",   # 其實URL
    ]
 
    def parse(self, response):
        # 訪問起始URL並獲取結果後的回調函數

關於windows的編碼問題
import sys,os
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')

3、開始項目

 1 import scrapy
 2 from scrapy.selector import HtmlXPathSelector
 3 from scrapy.http.request import Request
 4 
 5 
 6 class DigSpider(scrapy.Spider):
 7     # 爬蟲應用的名稱，經過此名稱啓動爬蟲命令
 8     name = "dig"
 9 
10     # 容許的域名
11     allowed_domains = ["chouti.com"]
12 
13     # 起始URL
14     start_urls = [
15         'http://dig.chouti.com/',
16     ]
17 
18     has_request_set = {}
19 
20     def parse(self, response):
21         print(response.url)
22 
23         hxs = HtmlXPathSelector(response)
24         page_list = hxs.select('//div[@id="dig_lcpage"]//a[re:test(@href, "/all/hot/recent/\d+")]/@href').extract()
25         for page in page_list:
26             page_url = 'http://dig.chouti.com%s' % page
27             key = self.md5(page_url)
28             if key in self.has_request_set:
29                 pass
30             else:
31                 self.has_request_set[key] = page_url
32                 obj = Request(url=page_url, method='GET', callback=self.parse)
33                 yield obj
34 
35     @staticmethod
36     def md5(val):
37         import hashlib
38         ha = hashlib.md5()
39         ha.update(bytes(val, encoding='utf-8'))
40         key = ha.hexdigest()
41         return key

執行此爬蟲文件，則在終端進入項目目錄執行以下命令：

scrapy crawl dig --nolog

對於上述代碼重要之處在於：

• Request是一個封裝用戶請求的類，在回調函數中yield該對象表示繼續訪問
• HtmlXpathSelector用於結構化HTML代碼並提供選擇器功能

4、scrapy的選擇器

#!/usr/bin/env python
# -*- coding:utf-8 -*-
from scrapy.selector import Selector, HtmlXPathSelector
from scrapy.http import HtmlResponse
html = """<!DOCTYPE html>
<html>
    <head lang="en">
        <meta charset="UTF-8">
        <title></title>
    </head>
    <body>
        <ul>
            <li class="item-"><a id='i1' href="link.html">first item</a></li>
            <li class="item-0"><a id='i2' href="llink.html">first item</a></li>
            <li class="item-1"><a href="llink2.html">second item<span>vv</span></a></li>
        </ul>
        <div><a href="llink2.html">second item</a></div>
    </body>
</html>
"""
response = HtmlResponse(url='http://example.com', body=html,encoding='utf-8')
# hxs = HtmlXPathSelector(response)
# print(hxs)
# hxs = Selector(response=response).xpath('//a')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[2]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[@id]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[@id="i1"]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[@href="link.html"][@id="i1"]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[contains(@href, "link")]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[starts-with(@href, "link")]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[re:test(@id, "i\d+")]')
# print(hxs)
# hxs = Selector(response=response).xpath('//a[re:test(@id, "i\d+")]/text()').extract()
# print(hxs)
# hxs = Selector(response=response).xpath('//a[re:test(@id, "i\d+")]/@href').extract()
# print(hxs)
# hxs = Selector(response=response).xpath('/html/body/ul/li/a/@href').extract()
# print(hxs)
# hxs = Selector(response=response).xpath('//body/ul/li/a/@href').extract_first()
# print(hxs)

# ul_list = Selector(response=response).xpath('//body/ul/li')
# for item in ul_list:
#     v = item.xpath('./a/span')
#     # 或
#     # v = item.xpath('a/span')
#     # 或
#     # v = item.xpath('*/a/span')
#     print(v)

# -*- 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):
    # 爬蟲應用的名稱，經過此名稱啓動爬蟲命令
    name = "chouti"
    # 容許的域名
    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)

自動登陸抽屜並點贊

注意：settings.py中設置DEPTH_LIMIT = 1來指定「遞歸」的層數。

5、格式化處理

上述實例只是簡單的處理，因此在parse方法中直接處理。若是對於想要獲取更多的數據處理，則能夠利用Scrapy的items將數據格式化，而後統一交由pipelines來處理。

import scrapy
from scrapy.selector import HtmlXPathSelector
from scrapy.http.request import Request
from scrapy.http.cookies import CookieJar
from scrapy import FormRequest


class XiaoHuarSpider(scrapy.Spider):
    # 爬蟲應用的名稱，經過此名稱啓動爬蟲命令
    name = "xiaohuar"
    # 容許的域名
    allowed_domains = ["xiaohuar.com"]

    start_urls = [
        "http://www.xiaohuar.com/list-1-1.html",
    ]
    # custom_settings = {
    #     'ITEM_PIPELINES':{
    #         'spider1.pipelines.JsonPipeline': 100
    #     }
    # }
    has_request_set = {}

    def parse(self, response):
        # 分析頁面
        # 找到頁面中符合規則的內容（校花圖片），保存
        # 找到全部的a標籤，再訪問其餘a標籤，一層一層的搞下去

        hxs = HtmlXPathSelector(response)

        items = hxs.select('//div[@class="item_list infinite_scroll"]/div')
        for item in items:
            src = item.select('.//div[@class="img"]/a/img/@src').extract_first()
            name = item.select('.//div[@class="img"]/span/text()').extract_first()
            school = item.select('.//div[@class="img"]/div[@class="btns"]/a/text()').extract_first()
            url = "http://www.xiaohuar.com%s" % src
            from ..items import XiaoHuarItem
            obj = XiaoHuarItem(name=name, school=school, url=url)
            yield obj

        urls = hxs.select('//a[re:test(@href, "http://www.xiaohuar.com/list-1-\d+.html")]/@href')
        for url in urls:
            key = self.md5(url)
            if key in self.has_request_set:
                pass
            else:
                self.has_request_set[key] = url
                req = Request(url=url,method='GET',callback=self.parse)
                yield req

    @staticmethod
    def md5(val):
        import hashlib
        ha = hashlib.md5()
        ha.update(bytes(val, encoding='utf-8'))
        key = ha.hexdigest()
        return key

spiders/xiahuar.py

import scrapy


class XiaoHuarItem(scrapy.Item):
    name = scrapy.Field()
    school = scrapy.Field()
    url = scrapy.Field()

items

import json
import os
import requests


class JsonPipeline(object):
    def __init__(self):
        self.file = open('xiaohua.txt', 'w')

    def process_item(self, item, spider):
        v = json.dumps(dict(item), ensure_ascii=False)
        self.file.write(v)
        self.file.write('\n')
        self.file.flush()
        return item


class FilePipeline(object):
    def __init__(self):
        if not os.path.exists('imgs'):
            os.makedirs('imgs')

    def process_item(self, item, spider):
        response = requests.get(item['url'], stream=True)
        file_name = '%s_%s.jpg' % (item['name'], item['school'])
        with open(os.path.join('imgs', file_name), mode='wb') as f:
            f.write(response.content)
        return item

pipelines

ITEM_PIPELINES = {
   'spider1.pipelines.JsonPipeline': 100,
   'spider1.pipelines.FilePipeline': 300,
}
# 每行後面的整型值，肯定了他們運行的順序，item按數字從低到高的順序，經過pipeline，一般將這些數字定義在0-1000範圍內。

settings

對於pipeline能夠作更多，以下：

from scrapy.exceptions import DropItem

class CustomPipeline(object):
    def __init__(self,v):
        self.value = v

    def process_item(self, item, spider):
        # 操做並進行持久化

        # return表示會被後續的pipeline繼續處理
        return item

        # 表示將item丟棄，不會被後續pipeline處理
        # raise DropItem()


    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化時候，用於建立pipeline對象
        :param crawler: 
        :return: 
        """
        val = crawler.settings.getint('MMMM')
        return cls(val)

    def open_spider(self,spider):
        """
        爬蟲開始執行時，調用
        :param spider: 
        :return: 
        """
        print('000000')

    def close_spider(self,spider):
        """
        爬蟲關閉時，被調用
        :param spider: 
        :return: 
        """
        print('111111')

自定義pipeline

6、中間件

class SpiderMiddleware(object):

    def process_spider_input(self,response, spider):
        """
        下載完成，執行，而後交給parse處理
        :param response: 
        :param spider: 
        :return: 
        """
        pass

    def process_spider_output(self,response, result, spider):
        """
        spider處理完成，返回時調用
        :param response:
        :param result:
        :param spider:
        :return: 必須返回包含 Request 或 Item 對象的可迭代對象(iterable)
        """
        return result

    def process_spider_exception(self,response, exception, spider):
        """
        異常調用
        :param response:
        :param exception:
        :param spider:
        :return: None,繼續交給後續中間件處理異常；含 Response 或 Item 的可迭代對象(iterable)，交給調度器或pipeline
        """
        return None


    def process_start_requests(self,start_requests, spider):
        """
        爬蟲啓動時調用
        :param start_requests:
        :param spider:
        :return: 包含 Request 對象的可迭代對象
        """
        return start_requests

爬蟲中間件

class DownMiddleware1(object):
    def process_request(self, request, spider):
        """
        請求須要被下載時，通過全部下載器中間件的process_request調用
        :param request: 
        :param spider: 
        :return:  
            None,繼續後續中間件去下載；
            Response對象，中止process_request的執行，開始執行process_response
            Request對象，中止中間件的執行，將Request從新調度器
            raise IgnoreRequest異常，中止process_request的執行，開始執行process_exception
        """
        pass



    def process_response(self, request, response, spider):
        """
        spider處理完成，返回時調用
        :param response:
        :param result:
        :param spider:
        :return: 
            Response 對象：轉交給其餘中間件process_response
            Request 對象：中止中間件，request會被從新調度下載
            raise IgnoreRequest 異常：調用Request.errback
        """
        print('response1')
        return response

    def process_exception(self, request, exception, spider):
        """
        當下載處理器(download handler)或 process_request() (下載中間件)拋出異常
        :param response:
        :param exception:
        :param spider:
        :return: 
            None：繼續交給後續中間件處理異常；
            Response對象：中止後續process_exception方法
            Request對象：中止中間件，request將會被從新調用下載
        """
        return None

下載器中間件

下載器中間件

7、自定義命令

• 在spiders同級建立任意目錄，如：commands
• 在其中建立 crawlall.py 文件 （此處文件名就是自定義的命令）

　　

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()

crawlall.py

• 在settings.py 中添加配置 COMMANDS_MODULE = '項目名稱.目錄名稱'
• 在項目目錄執行命令：scrapy crawlall 

8、自定義擴展

自定義擴展時，利用信號在指定位置註冊制定操做

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')

自定義擴展

9、避免重複訪問

scrapy默認使用 scrapy.dupefilter.RFPDupeFilter 進行去重，相關配置有：

DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter'
DUPEFILTER_DEBUG = False
JOBDIR = "保存範文記錄的日誌路徑，如：/root/"  # 最終路徑爲 /root/requests.seen　　

class RepeatUrl:
    def __init__(self):
        self.visited_url = set()

    @classmethod
    def from_settings(cls, settings):
        """
        初始化時，調用
        :param settings: 
        :return: 
        """
        return cls()

    def request_seen(self, request):
        """
        檢測當前請求是否已經被訪問過
        :param request: 
        :return: True表示已經訪問過；False表示未訪問過
        """
        if request.url in self.visited_url:
            return True
        self.visited_url.add(request.url)
        return False

    def open(self):
        """
        開始爬去請求時，調用
        :return: 
        """
        print('open replication')

    def close(self, reason):
        """
        結束爬蟲爬取時，調用
        :param reason: 
        :return: 
        """
        print('close replication')

    def log(self, request, spider):
        """
        記錄日誌
        :param request: 
        :param spider: 
        :return: 
        """
        print('repeat', request.url)

自定義URL去重操做

10、其餘

# -*- 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. 爬蟲名稱
BOT_NAME = 'step8_king'

# 2. 爬蟲應用路徑
SPIDER_MODULES = ['step8_king.spiders']
NEWSPIDER_MODULE = 'step8_king.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# 3. 客戶端 user-agent請求頭
# USER_AGENT = 'step8_king (+http://www.yourdomain.com)'

# Obey robots.txt rules
# 4. 禁止爬蟲配置
# ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# 5. 併發請求數
# 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. 延遲下載秒數
# DOWNLOAD_DELAY = 2


# The download delay setting will honor only one of:
# 7. 單域名訪問併發數，而且延遲下次秒數也應用在每一個域名
# CONCURRENT_REQUESTS_PER_DOMAIN = 2
# 單IP訪問併發數，若是有值則忽略：CONCURRENT_REQUESTS_PER_DOMAIN，而且延遲下次秒數也應用在每一個IP
# CONCURRENT_REQUESTS_PER_IP = 3

# Disable cookies (enabled by default)
# 8. 是否支持cookie，cookiejar進行操做cookie
# COOKIES_ENABLED = True
# COOKIES_DEBUG = True

# Disable Telnet Console (enabled by default)
# 9. Telnet用於查看當前爬蟲的信息，操做爬蟲等...
#    使用telnet ip port ，而後經過命令操做
# TELNETCONSOLE_ENABLED = True
# TELNETCONSOLE_HOST = '127.0.0.1'
# TELNETCONSOLE_PORT = [6023,]


# 10. 默認請求頭
# 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. 定義pipeline處理請求
# ITEM_PIPELINES = {
#    'step8_king.pipelines.JsonPipeline': 700,
#    'step8_king.pipelines.FilePipeline': 500,
# }



# 12. 自定義擴展，基於信號進行調用
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#     # 'step8_king.extensions.MyExtension': 500,
# }


# 13. 爬蟲容許的最大深度，能夠經過meta查看當前深度；0表示無深度
# DEPTH_LIMIT = 3

# 14. 爬取時，0表示深度優先Lifo(默認)；1表示廣度優先FiFo

# 後進先出，深度優先
# DEPTH_PRIORITY = 0
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleLifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.LifoMemoryQueue'
# 先進先出，廣度優先

# DEPTH_PRIORITY = 1
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleFifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.FifoMemoryQueue'

# 15. 調度器隊列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'
# from scrapy.core.scheduler import Scheduler


# 16. 訪問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. 自動限速算法
    from scrapy.contrib.throttle import AutoThrottle
    自動限速設置
    1. 獲取最小延遲 DOWNLOAD_DELAY
    2. 獲取最大延遲 AUTOTHROTTLE_MAX_DELAY
    3. 設置初始下載延遲 AUTOTHROTTLE_START_DELAY
    4. 當請求下載完成後，獲取其"鏈接"時間 latency，即：請求鏈接到接受到響應頭之間的時間
    5. 用於計算的... AUTOTHROTTLE_TARGET_CONCURRENCY
    target_delay = latency / self.target_concurrency
    new_delay = (slot.delay + target_delay) / 2.0 # 表示上一次的延遲時間
    new_delay = max(target_delay, new_delay)
    new_delay = min(max(self.mindelay, new_delay), self.maxdelay)
    slot.delay = new_delay
"""

# 開始自動限速
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# 初始下載延遲
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# 最大下載延遲
# AUTOTHROTTLE_MAX_DELAY = 10
# The average number of requests Scrapy should be sending in parallel to each remote server
# 平均每秒併發數
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:
# 是否顯示
# 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. 啓用緩存
    目的用於將已經發送的請求或相應緩存下來，以便之後使用
    
    from scrapy.downloadermiddlewares.httpcache import HttpCacheMiddleware
    from scrapy.extensions.httpcache import DummyPolicy
    from scrapy.extensions.httpcache import FilesystemCacheStorage
"""
# 是否啓用緩存策略
# HTTPCACHE_ENABLED = True

# 緩存策略：全部請求均緩存，下次在請求直接訪問原來的緩存便可
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.DummyPolicy"
# 緩存策略：根據Http響應頭：Cache-Control、Last-Modified 等進行緩存的策略
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"

# 緩存超時時間
# HTTPCACHE_EXPIRATION_SECS = 0

# 緩存保存路徑
# HTTPCACHE_DIR = 'httpcache'

# 緩存忽略的Http狀態碼
# HTTPCACHE_IGNORE_HTTP_CODES = []

# 緩存存儲的插件
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'


"""
19. 代理，須要在環境變量中設置
    from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
    
    方式一：使用默認
        os.environ
        {
            http_proxy:http://root:woshiniba@192.168.11.11:9999/
            https_proxy:http://192.168.11.11:9999/
        }
    方式二：使用自定義下載中間件
    
    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訪問
    Https訪問時有兩種狀況：
    1. 要爬取網站使用的可信任證書(默認支持)
        DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
        DOWNLOADER_CLIENTCONTEXTFACTORY = "scrapy.core.downloader.contextfactory.ScrapyClientContextFactory"
        
    2. 要爬取網站使用的自定義證書
        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對象
                    certificate=v2,  # X509對象
                    verify=False,
                    method=getattr(self, 'method', getattr(self, '_ssl_method', None))
                )
    其餘：
        相關類
            scrapy.core.downloader.handlers.http.HttpDownloadHandler
            scrapy.core.downloader.webclient.ScrapyHTTPClientFactory
            scrapy.core.downloader.contextfactory.ScrapyClientContextFactory
        相關配置
            DOWNLOADER_HTTPCLIENTFACTORY
            DOWNLOADER_CLIENTCONTEXTFACTORY

"""



"""
21. 爬蟲中間件
    class SpiderMiddleware(object):

        def process_spider_input(self,response, spider):
            '''
            下載完成，執行，而後交給parse處理
            :param response: 
            :param spider: 
            :return: 
            '''
            pass
    
        def process_spider_output(self,response, result, spider):
            '''
            spider處理完成，返回時調用
            :param response:
            :param result:
            :param spider:
            :return: 必須返回包含 Request 或 Item 對象的可迭代對象(iterable)
            '''
            return result
    
        def process_spider_exception(self,response, exception, spider):
            '''
            異常調用
            :param response:
            :param exception:
            :param spider:
            :return: None,繼續交給後續中間件處理異常；含 Response 或 Item 的可迭代對象(iterable)，交給調度器或pipeline
            '''
            return None
    
    
        def process_start_requests(self,start_requests, spider):
            '''
            爬蟲啓動時調用
            :param start_requests:
            :param spider:
            :return: 包含 Request 對象的可迭代對象
            '''
            return start_requests
    
    內置爬蟲中間件：
        '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. 下載中間件
    class DownMiddleware1(object):
        def process_request(self, request, spider):
            '''
            請求須要被下載時，通過全部下載器中間件的process_request調用
            :param request:
            :param spider:
            :return:
                None,繼續後續中間件去下載；
                Response對象，中止process_request的執行，開始執行process_response
                Request對象，中止中間件的執行，將Request從新調度器
                raise IgnoreRequest異常，中止process_request的執行，開始執行process_exception
            '''
            pass
    
    
    
        def process_response(self, request, response, spider):
            '''
            spider處理完成，返回時調用
            :param response:
            :param result:
            :param spider:
            :return:
                Response 對象：轉交給其餘中間件process_response
                Request 對象：中止中間件，request會被從新調度下載
                raise IgnoreRequest 異常：調用Request.errback
            '''
            print('response1')
            return response
    
        def process_exception(self, request, exception, spider):
            '''
            當下載處理器(download handler)或 process_request() (下載中間件)拋出異常
            :param response:
            :param exception:
            :param spider:
            :return:
                None：繼續交給後續中間件處理異常；
                Response對象：中止後續process_exception方法
                Request對象：中止中間件，request將會被從新調用下載
            '''
            return None

    
    默認下載中間件
    {
        '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,
# }

sittings

11、TinyScrapy

#!/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()

參考版

 

備註： 更多文檔參見：http://scrapy-chs.readthedocs.io/zh_CN/latest/index.html