Scrapy框架基本使用

崔庆才老师爬虫的学习笔记。

一、基本使用

1、目标站点

http://quotes.toscrape.com/

2、流程框架

(1)抓取第一页

请求第一页URL并得到源代码，进行下一步分析。

(2)获取内容和下一页链接

分析源代码，获取首页内容，获取下一页链接等待进一步爬取。

(3)翻页爬取

请求下一页信息，分析内容并请求再下一页链接。

(4)保存爬取结果

将爬取结果保存为特定格式如文本、数据库。

3、爬虫实战

命令行输入：

新建工程：scrapy startproject quotetutroial

进入目录：cd quotetutroial

生成爬虫：scrapy genspider quotes quotes.toscrape.com

项目结构：

• scrapy.cfg 配置文件

• items.py 保存数据的数据结构

• middlewares.py 爬取过程中定义的一些中间件

• pipelines.py 项目管道，可以输出一些items

• settings.py 定义的一些配置信息

• spider/quotes.py 主要的运行代码

运行爬虫：scrapy crawl quotes

4、项目代码

quotetutroial / scrapy.cfg

# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.io/en/latest/deploy.html

[settings]
default = quotetutroial.settings

[deploy]
#url = http://localhost:6800/
project = quotetutroial

quotetutroial / quotetutroial / items.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class QuoteItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 爬取完后，一个一个进行赋值，生成一个整体
    text = scrapy.Field()
    author = scrapy.Field()
    tags = scrapy.Field()

quotetutroial / quotetutroial / middlewares.py

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals

class QuotetutroialSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class QuotetutroialDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

quotetutroial / quotetutroial / pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

import pymongo
from scrapy.exceptions import DropItem

class TextPipeline(object):

    def __init__(self):
        self.limit = 50

    def process_item(self, item, spider):
        if item['text']:
            if len(item['text']) > self.limit:
                item['text'] = item['text'][0:self.limit].rstrip() + '...'
                return item
        else:
            return DropItem('Missing Text')

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):  # from_crawler方法可以从setting.py里拿到相应的配置信息
        return cls(
            mongo_uri=crawler.settings.get('MONGO_URI'),
            mongo_db=crawler.settings.get('MONGO_DB')
        )  # 这是一个类方法，需要返回一个class对象

    def open_spider(self, spider):  # open_spider方法定义爬虫将要启动时的操作
        self.client = pymongo.MongoClient(self.mongo_uri)
        self.db = self.client[self.mongo_db]

    def process_item(self, item, spider):
        name = item.__class__.__name__  # 将item的名称传给下边db表名
        self.db[name].insert(dict(item))
        return item

    def close_spider(self, spider):
        self.client.close()
    # 要想pipeline生效，需要在settings.py里指定ITEM_PIPELINES,序号越小优先级越高
    # 这里指定了两个pipeline，假设删掉一个pipline，那么只会执行另外一个pipline

quotetutroial / quotetutroial / settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for quotetutroial project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'quotetutroial'

SPIDER_MODULES = ['quotetutroial.spiders']
NEWSPIDER_MODULE = 'quotetutroial.spiders'

MONGO_URI = 'localhost'
MONGO_DB = 'quotestutorial'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'quotetutroial (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'quotetutroial.middlewares.QuotetutroialSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'quotetutroial.middlewares.QuotetutroialDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    #'quotetutroial.pipelines.TextPipeline': 300,
    'quotetutroial.pipelines.MongoPipeline': 400,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

quotetutroial / quotetutroial / spiders / quotes.py

# -*- coding: utf-8 -*-

import scrapy
from quotetutroial.items import QuoteItem

class QuotesSpider(scrapy.Spider):
    name = 'quotes'
    allowed_domains = ['quotes.toscrape.com']
    start_urls = ['http://quotes.toscrape.com/']

    def parse(self, response):
        quotes = response.css('.quote')
        for quote in quotes:
            item = QuoteItem()
            text = quotes.css('.text::text').extract_first()  # ::text是scrapy的语法格式，表示获取文本
            author = quotes.css('.author::text').extract_first()  # extract_first()表示获取第一个结果
            tags = quotes.css('.tags .tag::text').extract()  # extract()表示获取所有结果
            # 这里可以在终端里使用命令scrapy shell quotes.toscrape.com进入交互模式！！！
            # 输入exit()退出交互模式
            item['text'] = text
            item['author'] = author
            item['tags'] = tags
            yield item

        next = response.css('.pager .next a::attr(href)').extract_first()
        url = response.urljoin(next)  # 因为next是不完全的url，所以需要调用urljoin生成完整的url
        yield scrapy.Request(url=url, callback=self.parse)  # 回调自身parse，实现翻页
        # 此时可以命令行输入命令scrapy crawl quotes -o quotes.json保存数据
        # 还可以输入命令scrapy crawl quotes -o quotes.jl保存数据成json line格式
        # 还可以输入命令scrapy crawl quotes -o quotes.csv保存数据成csv格式
        # 还可以输入命令scrapy crawl quotes -o quotes.xml保存数据成xml格式
        # 还可以输入命令scrapy crawl quotes -o quotes.pickle保存数据成pickle格式
        # 还可以输入命令scrapy crawl quotes -o quotes.marshal保存数据成marshal格式
        # 还可以输入命令scrapy crawl quotes -o ftp://user:pass@ftp.example.com/path/quotes.csv保存数据到ftp服务器

持续更新…

最后更新： 2018年08月21日 17:48

原始链接： http://pythonfood.github.io/2018/07/05/Scrapy框架基本使用/

Python Food

赏

× 多少都行~