Scrapy 中常用的中间件和管道组件

Pipeline用法

储存到MongoDB

pipline.py中的代码

import pymongo

class MongoPipeline(object):
    def __init__(self, mongo_uri, mongo_db):
        self.mongo_uri = mongo_uri
        self.mongo_db = mongo_db

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URI'),
            mongo_db=crawler.settings.get('MONGO_DB')
        )

    def open_spider(self, spider):
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]

    def process_item(self, item, spider):
        name = item.collection
        self.db[name].insert(dict(item))
        return item

    def close_spider(self, spider):
        self.client.close()

settings配置

MONGO_URI = 'localhost'  # 若为远程MongoDB，需更改地址
MONGO_DB = 'images360'

ITEM_PIPELINES = {
        'images360.pipelines.MongoPipeline': 301,
}

存储到MySQL

pipeline 文件配置

import pymysql

class MysqlPipeline():
    def __init__(self, host, database, user, password, port):
        self.host = host
        self.database = database
        self.user = user
        self.password = password
        self.port = port

    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            host=crawler.settings.get('MYSQL_HOST'),
            database=crawler.settings.get('MYSQL_DATABASE'),
            user=crawler.settings.get('MYSQL_USER'),
            password=crawler.settings.get('MYSQL_PASSWORD'),
            port=crawler.settings.get('MYSQL_PORT'),
        )

    def open_spider(self, spider):
        self.db = pymysql.connect(self.host, self.user, self.password, self.database, charset='utf8',
                                  port=self.port)
        self.cursor = self.db.cursor()

    def close_spider(self, spider):
        self.db.close()

    def process_item(self, item, spider):
        print(item['title'])
        data = dict(item)
        keys = ', '.join(data.keys())
        values = ', '.join(['%s'] * len(data))
        sql = 'insert into %s (%s) values (%s)' % (item.table, keys, values)  # 动态构造数据，需先在MySQL里面创建好。
        self.cursor.execute(sql, tuple(data.values()))
        self.db.commit()
        return item

setting配置

MYSQL_HOST = 'localhost'  # 远程连接的话，要改成该主机数据库
MYSQL_DATABASE = 'images360'
MYSQL_USER = 'root'
MYSQL_PASSWORD = 'root'
MYSQL_PORT = 3306

ITEM_PIPELINES = {
        'images360.pipelines.MysqlPipeline': 302,
}

图片储存

pipline

from scrapy import Request
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline

class ImagePipeline(ImagesPipeline):
    def file_path(self, request, response=None, info=None):
        url = request.url
        file_name = url.split('/')[-1]
        return file_name

    def item_completed(self, results, item, info):
        image_paths = [x['path'] for ok, x in results if ok]
        if not image_paths:
            raise DropItem('Image Downloaded Failed')
        return item

    def get_media_requests(self, item, info):
        yield Request(item['url'])

settings配置

MYSQL_HOST = 'localhost'  # 远程连接的话，要改成该主机数据库
MYSQL_DATABASE = 'images360'
MYSQL_USER = 'root'
MYSQL_PASSWORD = 'root'
MYSQL_PORT = 3306

ITEM_PIPELINES = {
        'images360.pipelines.ImagePipeline': 300,
}

中间件使用

随机请求头

import random

class RandomUserAgentMiddleware():
    def __init__(self):
        self.user_agents = [
            'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
            'Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)',
            'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.2 (KHTML, like Gecko) Chrome/22.0.1216.0 Safari/537.2',
            'Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:15.0) Gecko/20100101 Firefox/15.0.1',
            'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
            'Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11',
            'ozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
            'Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/60.0',
            "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
            "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
            "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
            "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
            "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
            "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
            "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
            "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
            "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
            "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
            "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
            "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
            "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
        ]

    def process_request(self, request, spider):
        request.headers['User-Agent'] = random.choice(self.user_agents)

settings配置

DOWNLOADER_MIDDLEWARES = {
    'fangtianxia.middlewares.RandomUserAgentMiddleware': 545,
}

设置随机代理池

import logging
import requests

class ProxyMiddleware():
    def __init__(self, proxy_url):
        self.logger = logging.getLogger(__name__)
        self.proxy_url = proxy_url

    def get_random_proxy(self):
        try:
            response = requests.get(self.proxy_url)
            if response.status_code == 200:
                proxy = response.text
                return proxy
        except requests.ConnectionError:
            return False

    def process_request(self, request, spider):
        if request.meta.get('retry_times'):
            proxy = self.get_random_proxy()
            if proxy:
                uri = 'https://{proxy}'.format(proxy=proxy)
                self.logger.debug('使用代理 ' + uri)
                request.meta['proxy'] = uri

    @classmethod
    def from_crawler(cls, crawler):
        settings = crawler.settings
        return cls(
            proxy_url=settings.get('PROXY_URL')
        )

下载中间件配置

DOWNLOADER_MIDDLEWARES = {
    'fangtianxia.middlewares.ProxyMiddleware': 543,
}

末尾代理池配置

PROXY_URL = 'http://localhost:5555/random'  # 若为远程服务器运行，需更改地址

对接selenium

from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from scrapy.http import HtmlResponse
from logging import getLogger
import time

class SeleniumMiddleware():
    # def __init__(self, timeout=None, service_args=[]):
    def __init__(self, timeout=None):
        self.logger = getLogger(__name__)
        self.timeout = timeout
        # self.browser = webdriver.PhantomJS(service_args=service_args)
        self.browser = webdriver.Chrome()
        self.browser.set_window_size(1400, 700)
        self.browser.set_page_load_timeout(self.timeout)
        self.wait = WebDriverWait(self.browser, self.timeout)

    def __del__(self):
        self.browser.close()

    def process_request(self, request, spider):
        """
        用PhantomJS抓取页面
        :param request: Request对象
        :param spider: Spider对象
        :return: HtmlResponse
        """
        self.logger.debug('PhantomJS is Starting')
        page = request.meta.get('page', 1)
        try:
            self.browser.get(request.url)
            if page > 1:
                input = self.wait.until(
                    EC.presence_of_element_located((By.CSS_SELECTOR, '#q')))
                submit = self.wait.until(
                    EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_TSearchForm > div.search-button > button')))
                input.clear()
                input.send_keys(page)
                submit.click()
            self.wait.until(
                EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#mainsrp-pager li.item.active > span'), str(page)))
            self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.m-itemlist .items .item')))
            return HtmlResponse(url=request.url, body=self.browser.page_source, request=request, encoding='utf-8',
                                status=200)
        except TimeoutException:
            return HtmlResponse(url=request.url, status=500, request=request)

    @classmethod
    def from_crawler(cls, crawler):
        return cls(timeout=crawler.settings.get('SELENIUM_TIMEOUT'),
                   )
        # return cls(timeout=crawler.settings.get('SELENIUM_TIMEOUT'),
        #            service_args=crawler.settings.get('PHANTOMJS_SERVICE_ARGS'))

Settings配置

若需要更改为phantomjs，需把注释的内容替换出来，并在setting中增加设置：

SELENIUM_TIMEOUT = 20

PHANTOMJS_SERVICE_ARGS = ['--load-images=false', '--disk-cache=true']

原文链接