码上行动1.2 scrapy

最新推荐文章于 2023-07-01 18:05:05 发布

慢慢慢时光

最新推荐文章于 2023-07-01 18:05:05 发布

阅读量276

点赞数

分类专栏：爬虫

本文链接：https://blog.csdn.net/wjl31802/article/details/84134648

版权

爬虫专栏收录该内容

8 篇文章 0 订阅

订阅专栏

像读文献一样，读好的代码

tutorial

start.py

from scrapy import cmdline

cmdline.execute("scrapy crawl quotes".split())

totorial

spiders

quotes.py

# -*- coding: utf-8 -*-
import scrapy
from tutorial.items import QuoteItem

class QuotesSpider(scrapy.Spider):
    name = 'quotes'
    allowed_domains = ["quotes.toscrape.com"]
    start_urls = ['http://quotes.toscrape.com/page/1/']

    # def parse(self, response):
    #     quotes = response.css('.quote')
    #     for quote in quotes:
    #         item = QuoteItem()
    #         item['text'] = quote.css('.text::text').extract_first()
    #         item['author'] = quote.css('.author::text').extract_first()
    #         item['tags'] = quote.css('.tag .tag::text').extract()
    #         yield item
    #
    #     next = response.css('.page .next a::attr("href")').extract_first()
    #     url = response.urljoin(next)
    #     print(url)
    #     yield scrapy.Request(url=url, callback=self.parse)

    def parse(self, response):
        quotes = response.xpath('//div[@class="col-md-8"]/div')
        for quote in quotes:
            item = QuoteItem()
            item['text'] = quote.css('.text::text').extract_first()
            item['author'] = quote.css('.author::text').extract_first()
            item['tags'] = ','.join(quote.xpath('.//div[@class="tags"]/a/text()').getall()).strip()
            yield item

        next = response.xpath('//nav/ul/li[@class="next"]/a/@href').get()
        url = response.urljoin(next)
        yield scrapy.Request(url=url, callback=self.parse)
        if not next:
            return

items.py

import scrapy


class QuoteItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # collection = scrapy.Field()
    text = scrapy.Field()
    author = scrapy.Field()
    tags = scrapy.Field()

pipelines.py

from scrapy.exceptions import DropItem
import pymongo


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):
        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.__class__.__name__
        self.db[name].insert(dict(item))
        return item

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

settings.py

ITEM_PIPELINES = {
    # 'tutorial.pipelines.TutorialPipeline': 300,
    'tutorial.pipelines.TextPipeline': 300,
    'tutorial.pipelines.MongoPipeline': 400,
}
MONGO_URI = 'localhost'
MONGO_DB = 'tutorial'

images360

spider

images.py

# -*- coding: utf-8 -*-
import json
from urllib.parse import urlencode

import scrapy
from scrapy import Request

from ..items import ImageItem


class ImagesSpider(scrapy.Spider):
    name = 'images'
    allowed_domains = ['images.so.com']
    start_urls = ['http://images.so.com/']

    def start_requests(self):
        data = {
       'q': '摄影',
       'src': 'srp',
       'correct': '摄影',
       'pn': '0',
       'ch':'',
        'ran': '0',
        'ras': '6',
        'cn': '0',
        'gn': '0',
        'kn': '38',
        }
        base_url = 'https://image.so.com/j?'
        for page in range(1, self.settings.get('MAX_PAGE')+1):
            data['sn'] = page * 60 + 38
            params = urlencode(data)
            # 利用urlencode()方法将字典转化为url的GET参数，构造完整URL，构造并生成Request
            url = base_url + params
            yield Request(url, self.parse)

    def parse(self, response):
        result = json.loads(response.text)
        for image in result.get('list'):
            item = ImageItem()
            item['id'] = image.get('id')
            item['url'] = image.get('img')
            item['title'] = image.get('title')
            item['thumb'] = image.get('_thumb')
            yield item

items.py

class ImageItem(Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 定义四个字段，图片的ID，链接，标题，缩略图，两个属性collection 和 table 都定义成images字符串，
    # 分别代表MongoDB存储的Collection名称和MySQL存储的表名称
    collection = table = 'image'
    id = Field()
    url = Field()
    title = Field()
    thumb = Field()

pipelines.py

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


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):
        self.db[item.collection].insert(dict(item))
        return item

    def close_spider(self, spider):
        self.client.close()
        
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):
        data = dict(item)
        keys = ','.join(data.keys())
        values = ','.join(['%s'] * len(data))
        sql = 'insert into %s (%s) values (%s)'%(item.table, keys, values)
        self.cursor.execute(sql, tuple(data.values()))
        self.db.commit()
        return item



# 专门处理下载的Pipeline,包括文件下载和图片下载
class ImagePipeline(ImagesPipeline):
    # 先定义存储文件的路径，需要IMAGES_STORE变量，= './images',内置的ImagesPipeline默认读取Item的image_urls字段
    # 现在生成的Item图片链接字段不是image_urls字段表示的，也不是列表，而是单个url，需要重新定义部分逻辑，自定义ImagePipeline
    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):
        # 单个item完成下载时的处理办法，results是该item对应的下载结果，列表，包含下载成功失败的信息，列表空，失败，dropitem，否则返回item
        image_path = [x['path'] for ok, x in results if ok]
        if not image_path:
            raise DropItem('Image Download Failed')
        return item

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

settings.py

ITEM_PIPELINES = {
   'images360.pipelines.ImagePipeline': 300,
   'images360.pipelines.MongoPipeline': 301,
   'images360.pipelines.MysqlPipeline': 302,
}
MAX_PAGE = 50

MONGO_URI = 'localhost'
MONGO_DB = 'images360'

MYSQL_HOST = 'localhost'
MYSQL_DATABASE = 'images360'
MYSQL_PORT = 3306
MYSQL_USER = 'root'
MYSQL_PASSWORD = 'Wangjinliang_45'

IMAGES_STORE = './images'

scrapyselenium淘宝

start.py

from scrapy import cmdline

cmdline.execute("scrapy crawl taobao".split())

spiders

taobao.py

# -*- coding: utf-8 -*-
from urllib.parse import quote
import scrapy
from scrapy import Request
from ..items import ProductItem

class TaobaoSpider(scrapy.Spider):
    name = 'taobao'
    allowed_domains = ['www.taobao.com']
    base_url = 'http://www.taobao.com/search?q='

    def start_requests(self):
        # 遍历分页页码，构造生成Request,分页页码用meta参数传递，设置dont_filter不去重
        # quote()方法将内容转化为URL编码的格式，中文字符
        for keyword in self.settings.get('KEYWORDS'):
            for page in range(1, self.settings.get('MAX_PAGE') + 1):
                url = self.base_url + quote(keyword)
                yield Request(url=url, callback=self.parse, meta={'page': page}, dont_filter=True)

    def parse(self, response):
        # xpath规则：//从匹配选择的当前节点选择文档中的节点，不考虑位置 最前面加.选取当前节点内部元素 [1]是谓语，选取第一个xxx
        # /text()节点的内部文本，具体内容extract() strip()删除开头结尾空字符 ''.join()序列中的元素以字符连接为新字符串
        products = response.xpath(
            '//div[@id="mainsrp-itemlist"]//div[@class="items"][1]//div[contains(@class, "item")]'
        )
        for product in products:
            item = ProductItem()
            item['price'] = ''.join(product.xpath('.//div[contains(@class, "price")]//text()').extract()).strip()
            item['title'] = ''.join(product.xpath('.//div[contains(@class, "title")]//text()').extract()).strip()
            item['shop'] = ''.join(product.xpath('.//div[contains(@class, "shop")]//text()').extract()).strip()
            item['image'] = ''.join(product.xpath('.//div[@class="pic"]//img[contains(@class, "img")]/@data-src').extract()).strip()
            item['deal'] = product.xpath('.//div[contains(@class, "deal-cnt")]//text()').extract_first()
            item['location'] = product.xpath('.//div[contains(@class, "location")]//text()').extract_first()
            yield item

pipelines.py

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):
        self.db[item.collection].insert(dict(item))

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

class ScrapyseleniumtestPipeline(object):
    def process_item(self, item, spider):
        return item

items.py

from scrapy import Field, Item

class ProductItem(Item):
    # 得到商品的图片、名称、价格、购买人数、店铺名称、店铺所在地
    collection = 'products'
    image = Field()
    price = Field()
    deal = Field()
    title = Field()
    shop = Field()
    location = Field()

middlewares.py

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


class SeleniumMiddleware():
    def __init__(self, timeout=None):
        self.logger = getLogger(__name__)
        self.timeout = timeout
        chrome_options = webdriver.ChromeOptions()
        chrome_options.add_argument('--headless')
        # self.browser = webdriver.PhantomJS(service_args=service_args)
        self.browser = webdriver.Chrome(chrome_options=chrome_options)
        # 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
        """
        # 通过request的meta属性获取当前需要爬取的页码
        # self.logger.debug('PhantomJS is starting')
        self.logger.debug('Chrome is starting')
        page = request.meta.get('page', 1)
        try:
            # 调用PhantomJS对象的get()方法访问Request对应的URL，随后处理等待和翻页
            self.browser.get(request.url)
            if page > 1:
                # 页码＞1，跳页操作，否则等待加载页面
                # 翻页操作：先获取页码输入框，赋值为input，然后获取“确定”按钮，赋值为submit，先清空输入框，clear()再调用
                # send_keys()方法将页码填充到输入框，点击“确定”
                input = self.wait.until(
                    EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > input'))
                )
                submit = self.wait.until(
                    EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')) )
                input.clear()
                input.send_keys(page)
                submit.click()
            # 确定跳转正确：判断当前高亮页码数是当前的页码数,css选择器和当前跳转的页码通过参数传给text_to_be...
            self.wait.until(EC.text_to_be_present_in_element(
                (By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(page)))
            # 最终要等到商品信息加载出来，选择器对应页面内容是每个商品的信息快
            self.wait.until(EC.presence_of_element_located(
                (By.CSS_SELECTOR, '.m-itemlist .items .item')))
            # 用PhantomJS对象的page_source属性获得当前页面的源代码，用它直接构造并返回一个HtmlResponse对象，需要传入多个参数
            # 如url,body等，是它的基础属性
            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.set

scrapyuniversal中华网

spiders

china.py

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from ..loader import ChinaLoader
from ..items import NewsItem


class ChinaSpider(CrawlSpider):
    name = 'china'
    allowed_domains = ['tech.china.com']
    start_urls = ['http://tech.china.com/articles']

    rules = (
        Rule(LinkExtractor(allow='article\/.*\.html', restrict_xpaths='//div[@id="left_side"]//div[@class="con_item"]'),
             callback='parse_item'),
        Rule(LinkExtractor(restrict_xpaths='//div[@id="pageStyle"]//a[contains(., "下一页")]'))
    )

    def parse_item(self, response):
        loader = ChinaLoader(item=NewsItem(), response=response)
        loader.add_xpath('title', '//h1[@id="chan_newsTitle"]/text()')
        loader.add_value('url', response.url)
        loader.add_xpath('text', '//div[@id="chan_newsDetail"]//text()')
        loader.add_xpath('datetime', '//div[@id="chan_newsInfo"]/text()', re='(\d+-\d+-\d+\s\d+:\d+:\d+)')
        loader.add_xpath('source', '//div[@id="chan_newsInfo"]/text()')
        loader.add_value('website', '中华网')
        yield loader.load_item()


        # item = NewsItem()
        # item['title'] = response.xpath('//h1[@id="chan_newsTitle"]/text()').extract_first()
        # item['url'] = response.url
        # item['text'] = ''.join(response.xpath('//div[@id="chan_newsDetail"]//text()').extract()).strip()
        # item['datetime'] = response.xpath('//div[@id="chan_newsInfo"]/text()').re_first('(\d+-\d+-\d+\s\d+:\d+:\d+)')
        # item['source'] = response.xpath('//div[@id="chan_newsInfo"]/text()').re_first('来源：(.*)').strip()
        # item['website'] = '中华网'
        # yield item

        # i = {}
        # #i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
        # #i['name'] = response.xpath('//div[@id="name"]').extract()
        # #i['description'] = response.xpath('//div[@id="description"]').extract()
        # return i

universal.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule

from ..rules import rules
from ..utils import get_config


class UniversalSpider(CrawlSpider):
    name = 'universal'
    def __init__(self, name, *args, **kwargs):
        config = get_config(name)
        self.config = config
        self.rules = rules.get(config.get('rules'))
        start_urls = config.get('start_urls')
        if start_urls:
            if start_urls.get('type') == 'static':
                self.start_urls = start_urls.get('value')
            elif start_urls.get('type') == 'dynamic':
                self.start_urls = list(eval('urls.' + start_urls.get('method'))(*start_urls.get('args', [])))
        self.allowed_domains = config.get('allowed_domains')
        super(UniversalSpider, self).__init__(*args, **kwargs)



    def parse_item(self, response):
        item = self.config.get('item')
        if item:
            cls = eval(item.get('class'))
            loader = eval(item.get('loader'))(cls, response=response)
            # 动态获取配置
            for key, value in item.get('attrs').items():
                for extractor in value:
                    if extractor.get('method') == 'xpath':
                        loader.add_xpath(key, *extractor.get('args'), **{'re': extractor.get('re')})
                    if extractor.get('method') == 'css':
                        loader.add_css(key, *extractor.get('args'), **{'re': extractor.get('re')})
                    if extractor.get('method') == 'value':
                        loader.add_value(key, *extractor.get('args'), **{'re': extractor.get('re')})
                    if extractor.get('method') == 'attr':
                        loader.add_value(key, *extractor.get('args'), **{'re': extractor.get('re')})
            yield loader.load_item()
            
        #i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
        #i['name'] = response.xpath('//div[@id="name"]').extract()
        #i['description'] = response.xpath('//div[@id="description"]').extract()

run.py

import sys

from scrapy.crawler import CrawlerProcess
from scrapy.utils.project import get_project_settings

from scrapyuniversal.scrapyuniversal.utils import get_config


def run():
    name = sys.argv[1]
    custom_settings = get_config(name)
    # 爬取使用的Spider名称
    spider = custom_settings.get('spider', 'universal')
    project_settings = get_project_settings()
    settings = dict(project_settings.copy())
    # 合并配置
    settings.update(custom_settings.get('settings'))
    process = CrawlerProcess(settings)
    # 启动爬虫
    process.crawl(spider, **{'name': name})
    process.start()

if __name__ == '__main__':
    run()

configs

china.json

{
  "spider": "universal",
  "website": "中华网科技",
  "type": "新闻",
  "index": "http://tech.china.com/",
  "settings": {
    "USER_AGENT": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"
  },
  "start_urls": {
    "type": "dynamic",
    "method": "china",
    "args": [
      5, 10
    ]
  },

  "allowed_domains": [
    "tech.china.com"
  ],
  "rules": "china",
  "item": {
    "class": "NewsItem",
    "loader": "ChinaLoader",
    "attrs": {
      "title": [
        {
          "method": "xpath",
          "args": [
            "//h1[@id='chan_newsTitle']/text()"
          ]
        }
      ],
      "url": [
        {
          "method": "attr",
          "args": [
            "url"
          ]
        }
      ],
      "text": [
        {
          "method": "xpath",
          "args": [
            "//div[@id='chan_newsDetail']//text()"
          ]
        }
      ],
      "datetime": [
        {
          "method": "xpath",
          "args": [
            "//div[@id='chan_newsInfo']/text()"
          ],
          "re": "(\\d+-\\d+-\\d+\\s\\d+:\\d+:\\d+)"
        }
      ],
      "source": [
        {
          "method": "xpath",
          "args": [
          "//div[@id='chan_newsInfo']/text()"
        ]
        }
      ],
      "website":[
        {
          "method": "value",
          "args": [
            "中华网"
          ]
        }
      ]
    }
  }
}
//将spider的属性抽离出来配置成JSON，第一个字段spider即Spider的名称，后面是站点的描述，站点名称、类型、首页等，随后的settings是该视频的天特有的settings配置
//随后是Spider的一些属性，start_url,allowed_domains,rules等

items.py

class NewsItem(Item):
    # 新闻标题、链接、正文、发布时间、来源、站点名称
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = Field()
    url = Field()
    text = Field()
    datetime = Field()
    source = Field()
    website = Field()

loader.py

from scrapy.loader import ItemLoader
from scrapy.loader.processors import TakeFirst, Compose, Join

# ChinaLoader继承了Newsloader类， 定义通用的Out Porcessor为TakeFirst,相当于之前定义的extract_first()方法的功能
class NewsLoader(ItemLoader):
    default_output_processor = TakeFirst()

# 定义text_out和source_out字段，使用Compose Porcessor，有两个参数，Join也是一个Processor可以把列表拼合成一个字符串，第二个参数
# 为匿名参数，将字符串的头尾空白字符去掉，从而将列表形式的提取结果转化为去除头尾空白的字符串
class ChinaLoader(NewsLoader):
    text_out = Compose(Join(), lambda s: s.strip())
    source_out = Compose(Join(), lambda s: s.strip())

rules.py

from scrapy.spiders import Rule
from scrapy.linkextractors import LinkExtractor

rules = {
    'china': (
        Rule(LinkExtractor(allow='article\/.*\.html', restrict_xpaths='//div[@id="left_side"]//div[@class="con_item"]'),
             callback='parse_item'),
        Rule(LinkExtractor(restrict_xpaths='//div[@id="pageStyle"]//a[contains(., "下一页")]'))
    )
}

urls.py

def china(start, end):
    for page in range(start, end + 1):
        yield 'http://tech.china.com/articles/index_' + str(page) + '.html'

utils.py

from os.path import realpath, dirname
import json

def get_config(name):
    path = dirname(realpath(__file__)) + '/configs' + name + '.json'
    with open(path, 'r', encoding='utf-8') as f:
        return json.loads(f.read())

README.md

通用爬虫

以中华网为例



目标：抓取新闻列表的所有分页的新闻详情，包括标题、正文、时间、来源等信息



项目梳理



新建项目、创建Spider

CrawlSpider,scrapy提供的通用Spider,命令 scrapy genspider -t crawl china tech.china.com Spider内容多了rules属性的定义,Rule管理爬取规则，包含提取和跟进页面的设置，第一个参数是LinkExtractor,默认回调函数不是parse, 而是parse_item

定义Rule,实现解析函数

先将start_urls修改为起始链接，然后Spider开始爬取start_urls的每一个链接，得到Response之后，Spider根据Rule提取 页面内的超链接，去生成进一步的Request

起始为新闻列表页，下一步提取每条新闻的详情页的链接 链接都在class为con_item的div节点里，用LinkExtractor的 restrict_xpaths属性指定，Spider从该区域提取所有超链接生成Request,但是每篇文章的导航中有其他的超链接标签，真正的 超链接路径以article开头，用正则匹配赋值给allow参数，对应页面就是详情页，是需要解析的，callback到parse_item

另外要让当前页面分页功能，提取下一页的链接，在ID为pageStyle的节点内，直接用LinkExtractor的restrict_xpaths属性 指定提取的链接，不用提取页面详情信息，不需要callback，下一页如果匹配成功，要像上述情况分析，加一个follow参数True ，代表继续跟进匹配分析，follow可以不加，默认

实现页面翻页和详情页的抓取了

解析页面

先定义Item,字段包括新闻标题、链接、正文、发布时间、来源、站点名称，站点名称赋值中华网，通用爬虫，所以需要字段区别站点名

如果和之前一样提取内容，调用response变量的xpath()等方法即可，parse_item()实现，把每条新闻信息提取成一个NewsItem对象

这种提取方式不规整，对Item的提取，用模块Item Loader,通过add_xpath()\add_css()\add_value()等方式实现配置化提取，改写 parse_item() 定义ItemLoader的子类，名为ChinaLoader ChinaLoader继承了Newsloader类， 定义通用的Out Porcessor为TakeFirst, 相当于之前定义的extract_first()方法的功能，返回第一个非空值 ChinaLoader中定义text_out和source_out字段，使用 Compose Porcessor，是用给定的多个函数组合构造的Processor,有两个参数，Join也是一个Processor可以把列表拼合成一个字符串， 第二个参数为匿名参数，将字符串的头尾空白字符去掉，从而将列表形式的提取结果转化为去除头尾空白的字符串

通用配置抽取

如果扩展其他站点，仍需要创建新的CrawlSpider，定义站点的Rule，单独实现parse_item()方法。许多代码是重复的，如 CrawkSpider的变量、方法名几乎一样，可以新建通用Spider，将name\allowed_domains等抽取，在Spider初始化时赋值即可 命令scrapy genspidet -t crawl universal universal将之前Spide内的属性抽离配置成Json,名为china.josn,放到 configs文件夹，和spiders文件夹并列

json代码说明：第一个字段spider为Spider的名称，universal，后面是站点描述，站点名、类型、首页等，随后的settings是 该Spider特有的settings配置，随后是spider的一些属性，start_urls、allowed_domains、rules等，rules也可单独定义为rules.py 做成配置文件，实现Rule的分离

启动爬虫，需要从该配置文件中读取动态加载到Spider，需要定义读取JSON文件的方法get_config()到utils文件中

定义入口文件run.py，放到根目录下，启动Spider 运行入口run(),先获取命令行的参数赋值为name，就是JSON文件的名称，也就是要 爬取网站的名称，先利用get_config()方法传入该名称读取刚才定义的配置文件，获取爬取使用的spider的名称、配置文件中的 settings配置，再把获取的settings配置和项目全局的settings配置合并，新建CrawlerProcess传入爬取使用的配置，调用 crawl()和start()方法启动爬取

在universal中，新建__init__方法初始化配置，赋值start_urls,allowed_domains,rules等属性，rules属性另外读取rules.py配置 实现基础配置，再讲剩下的解析部分也配置抽离出来，变量包括Item Loader类的选用、Item类的选用、Item Loader方法参数的定义

配置JSON文件中，class和loader属性分别代表Item和Item Loader所用的类，定义attrs属性定义每个字段的提取规则，如 title定义的每一项都有method属性，代表使用的提取方法，xpath代表调用Item Loader的add_xpath()方法，args即参数，add_xpath() 的第二个参数，即xpath表达式，针对datetime,还用了一次正则，定义re参数传递正则

最后，是加载配置到parse_item()方法，首先获取item的配置信息，然后获取class的配置，初始化Item Loader，遍历Item 的各个属性依次提取，判断method字段，调用对应处理方法

此外，start_urls的配置，某些情况，也需要动态配置，一种直接配置URL列表，一种调用方法生成，如果动态生成，调用方法传参数

慢慢慢时光

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
码上行动1.2 scrapy

像读文献一样，读好的代码文章目录tutorialstart.pytotorialspidersitems.pypipelines.pysettings.pyimages360spideritems.pypipelines.pysettings.pyscrapyselenium淘宝start.pyspiderspipelines.pyitems.pymiddlewares.pyscrapyu...
复制链接

扫一扫