class CrawlSpider(Spider):
    rules = ()
    def __init__(self, *a, **kw):
        super(CrawlSpider, self).__init__(*a, **kw)
        self._compile_rules()
    #首先調用parse()來處理start_urls中返回的response對象
    #parse()則將這些response對象傳遞給了_parse_response()函數處理，并設置回調函數為parse_start_url()
    #設置了跟進標志位True
    #parse將返回item和跟進了的Request對象    
    def parse(self, response):
        return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True)
    #處理start_url中返回的response，需要重寫
    def parse_start_url(self, response):
        return []
    def process_results(self, response, results):
        return results
    #從response中抽取符合任一用戶定義'規(guī)則'的鏈接，并構造成Resquest對象返回
    def _requests_to_follow(self, response):
        if not isinstance(response, HtmlResponse):
            return
        seen = set()
        #抽取之內的所有鏈接，只要通過任意一個'規(guī)則'，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]
            #使用用戶指定的process_links處理每個連接
            if links and rule.process_links:
                links = rule.process_links(links)
            #將鏈接加入seen集合，為每個鏈接生成Request對象，并設置回調函數為_repsonse_downloaded()
            for link in links:
                seen.add(link)
                #構造Request對象，并將Rule規(guī)則中定義的回調函數作為這個Request對象的回調函數
                r = Request(url=link.url, callback=self._response_downloaded)
                r.meta.update(rule=n, link_text=link.text)
                #對每個Request調用process_request()函數。該函數默認為indentify，即不做任何處理，直接返回該Request.
                yield rule.process_request(r)
    #處理通過rule提取出的連接，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對象，會用callback解析處理他，并返回request或Item對象
    def _parse_response(self, response, callback, cb_kwargs, follow=True):
        #首先判斷是否設置了回調函數。（該回調函數可能是rule中的解析函數，也可能是 parse_start_url函數）
        #如果設置了回調函數（parse_start_url()），那么首先用parse_start_url()處理response對象，
        #然后再交給process_results處理。返回cb_res的一個列表
        if callback:
            #如果是parse調用的，則會解析成Request對象
            #如果是rule callback，則會解析成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
        #如果需要跟進，那么使用定義的Rule規(guī)則提取并返回這些Request對象
        if follow and self._follow_links:
            #返回每個Request對象
            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 爬蟲任務名稱 爬取的范圍域

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 （分類列表的小吃）
 
    # 創(chuàng)建一個Rule對象(也創(chuàng)建一個LinkExtractor對象)
    rules = (
 
        # 菜單詳情地址
        # https://www.xiachufang.com/recipe/106909278/
        # https://www.xiachufang.com/recipe/1055105/
        Rule(LinkExtractor(allow=r".*?/recipe/\d+/$"), callback="parse_item", follow=False),
 
    )
 
    # 解析菜單詳情
    def parse_item(self, response):
        # 不需要手動構造item對象
        item = {}
        # print(response.url)
        # 圖片鏈接,名稱,評分,多少人做過,發(fā)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('的廚房','')
 
        # print(item)
 
        return item

import json
 
from itemadapter import ItemAdapter
 
 
class MeitouPipeline:
    """處理items對象的數據"""
    def __init__(self):
        self.file_=open('xcf-1.json','w',encoding='utf-8')
        print('文件打開了。。。')
 
    def process_item(self, item, spider):
        """item接收爬蟲器丟過來的items對象"""
        py_dict=dict(item) # 先把攜帶鍵值對數據items對象轉成字典
        #dict轉換成json數據
        json_data=json.dumps(py_dict,ensure_ascii=False)+",\n"
        #寫入
        self.file_.write(json_data)
        print("寫入數據...")
        return item
 
 
    def __del__(self):
        self.file_.close()  #關閉
        print('文件關閉了....')

# 全局用戶代理，默認是被注釋了，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
 
# 設置下載延時
DOWNLOAD_DELAY = 1
 
#開啟管道
ITEM_PIPELINES = {
   "Meitou.pipelines.MeitouPipeline": 300,
}