Python的Scrapy框架中的CrawlSpider介绍和使用

class CrawlSpider(Spider):
    rules = ()
    def __init__(self, *a, **kw):
        super(CrawlSpider, self).__init__(*a, **kw)
        self._compile_rules()
    #首先调用parse()来处理start_urls中返回的response对象
    #parse()则将这些response对象传递给了_parse_response()函数处理，并设置回调函数为parse_start_url()
    #设置了跟进标志位True
    #parse将返回item和跟进了的Request对象    
    def parse(self, response):
        return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True)
    #处理start_url中返回的response，需要重写
    def parse_start_url(self, response):
        return []
    def process_results(self, response, results):
        return results
    #从response中抽取符合任一用户定义'规则'的链接，并构造成Resquest对象返回
    def _requests_to_follow(self, response):
        if not isinstance(response, HtmlResponse):
            return
        seen = set()
        #抽取之内的所有链接，只要通过任意一个'规则'，即表示合法
        for n, rule in enumerate(self._rules):
            links = [l for l in rule.link_extractor.extract_links(response) if l not in seen]
            #使用用户指定的process_links处理每个连接
            if links and rule.process_links:
                links = rule.process_links(links)
            #将链接加入seen集合，为每个链接生成Request对象，并设置回调函数为_repsonse_downloaded()
            for link in links:
                seen.add(link)
                #构造Request对象，并将Rule规则中定义的回调函数作为这个Request对象的回调函数
                r = Request(url=link.url, callback=self._response_downloaded)
                r.meta.update(rule=n, link_text=link.text)
                #对每个Request调用process_request()函数。该函数默认为indentify，即不做任何处理，直接返回该Request.
                yield rule.process_request(r)
    #处理通过rule提取出的连接，并返回item以及request
    def _response_downloaded(self, response):
        rule = self._rules[response.meta['rule']]
        return self._parse_response(response, rule.callback, rule.cb_kwargs, rule.follow)
    #解析response对象，会用callback解析处理他，并返回request或Item对象
    def _parse_response(self, response, callback, cb_kwargs, follow=True):
        #首先判断是否设置了回调函数。（该回调函数可能是rule中的解析函数，也可能是 parse_start_url函数）
        #如果设置了回调函数（parse_start_url()），那么首先用parse_start_url()处理response对象，
        #然后再交给process_results处理。返回cb_res的一个列表
        if callback:
            #如果是parse调用的，则会解析成Request对象
            #如果是rule callback，则会解析成Item
            cb_res = callback(response, **cb_kwargs) or ()
            cb_res = self.process_results(response, cb_res)
            for requests_or_item in iterate_spider_output(cb_res):
                yield requests_or_item
        #如果需要跟进，那么使用定义的Rule规则提取并返回这些Request对象
        if follow and self._follow_links:
            #返回每个Request对象
            for request_or_item in self._requests_to_follow(response):
                yield request_or_item
    def _compile_rules(self):
        def get_method(method):
            if callable(method):
                return method
            elif isinstance(method, basestring):
                return getattr(self, method, None)
        self._rules = [copy.copy(r) for r in self.rules]
        for rule in self._rules:
            rule.callback = get_method(rule.callback)
            rule.process_links = get_method(rule.process_links)
            rule.process_request = get_method(rule.process_request)
    def set_crawler(self, crawler):
        super(CrawlSpider, self).set_crawler(crawler)
        self._follow_links = crawler.settings.getbool('CRAWLSPIDER_FOLLOW_LINKS', True)

scrapy startproject Meitou

cd Meitou

scrapy genspider -t crawl 爬虫任务名称 爬取的范围域

scrapy genspider -t crawl crawl_yjin xx.com

scrapy crawl crawl_yjin --nolog

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
 
 
class CrawlYjinSpider(CrawlSpider):
    name = "crawl_yjin"
    allowed_domains = ["xiachufang.com"]
    start_urls = ["https://www.xiachufang.com/category/40073/"]  # 起始url （分类列表的小吃）
 
    # 创建一个Rule对象(也创建一个LinkExtractor对象)
    rules = (
 
        # 菜单详情地址
        # https://www.xiachufang.com/recipe/106909278/
        # https://www.xiachufang.com/recipe/1055105/
        Rule(LinkExtractor(allow=r".*?/recipe/\d+/$"), callback="parse_item", follow=False),
 
    )
 
    # 解析菜单详情
    def parse_item(self, response):
        # 不需要手动构造item对象
        item = {}
        # print(response.url)
        # 图片链接,名称,评分,多少人做过,发布人
        item['imgs'] = response.xpath('//div/img/@src').get()
        #去除空格和\n
        item['title']=''.join(response.xpath('//div/h1/text()').get()).replace(' ','').replace('\n','')
        item['score']=response.xpath('//div[@class="score float-left"]/span[@class="number"]/text()').extract_first()
        item['number']=response.xpath('//div[@class="cooked float-left"]/span[@class="number"]/text()').get()
        item['author']=''.join(response.xpath('//div[@class="author"]/a/img/@alt').get()).replace('的厨房','')
 
        # print(item)
 
        return item

import json
 
from itemadapter import ItemAdapter
 
 
class MeitouPipeline:
    """处理items对象的数据"""
    def __init__(self):
        self.file_=open('xcf-1.json','w',encoding='utf-8')
        print('文件打开了。。。')
 
    def process_item(self, item, spider):
        """item接收爬虫器丢过来的items对象"""
        py_dict=dict(item) # 先把携带键值对数据items对象转成字典
        #dict转换成json数据
        json_data=json.dumps(py_dict,ensure_ascii=False)+",\n"
        #写入
        self.file_.write(json_data)
        print("写入数据...")
        return item
 
 
    def __del__(self):
        self.file_.close()  #关闭
        print('文件关闭了....')

# 全局用户代理，默认是被注释了，不生效
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36'
 
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
 
# 设置下载延时
DOWNLOAD_DELAY = 1
 
#开启管道
ITEM_PIPELINES = {
   "Meitou.pipelines.MeitouPipeline": 300,
}