(3).递归获取所有页码

# -*- coding: utf-8 -*-
import scrapy


class GetChoutiSpider(scrapy.Spider):
    name = ‘get_chouti‘
    allowed_domains = [‘chouti.com‘]
    start_urls = [‘https://dig.chouti.com/‘]

    def parse(self, response):
        # 在子子孙孙中找到所有id="dig_lcpage"的div标签
        # 在对应的div标签中找到所有的a标签
        # 获取所有对应a标签的href属性
        # 加上extract()获取字符串
        res = response.xpath(‘//div[@id="dig_lcpage"]//a/@href‘).extract()

        for url in res:
            print(url)
            ‘‘‘
            /all/hot/recent/2
            /all/hot/recent/3
            /all/hot/recent/4
            /all/hot/recent/5
            /all/hot/recent/6
            /all/hot/recent/7
            /all/hot/recent/8
            /all/hot/recent/9
            /all/hot/recent/10
            /all/hot/recent/2
            ‘‘‘
        # 会发现这里有重复的，因为我们起始是第一页，每次总共分十页。那么下一页指的就是第二页
        # 所以会发现第二页重复的href重复了

        # 可以定义一个集合
        urls = set()

        for url in res:
            if url in urls:
                print(f"{url}--此url已存在")
            else:
                urls.add(url)
                print(url)
        ‘‘‘
        /all/hot/recent/2
        /all/hot/recent/3
        /all/hot/recent/4
        /all/hot/recent/5
        /all/hot/recent/6
        /all/hot/recent/7
        /all/hot/recent/8
        /all/hot/recent/9
        /all/hot/recent/10
        /all/hot/recent/2--此url已存在

        ‘‘‘

# -*- coding: utf-8 -*-
import scrapy


class GetChoutiSpider(scrapy.Spider):
    name = ‘get_chouti‘
    allowed_domains = [‘chouti.com‘]
    start_urls = [‘https://dig.chouti.com/‘]

    def parse(self, response):
        # 上面是直接将url进行比较，但是一般情况下我们不直接比较url
        # url我们可能会放在缓存里，或者放在数据库里
        # 如果url很长，会占用空间，因此我们会进行一个加密，比较加密之后的结果
        res = response.xpath(‘//div[@id="dig_lcpage"]//a/@href‘).extract()
        # 也可以直接找到所有想要的a标签
        ‘‘‘
        找到a标签，什么样的a标签，以"/all/hot/recent/"开头的a标签
        res = response.xpath(‘//a[starts-with(@href, "/all/hot/recent/")]/@href‘).extract()
        
        也可以通过正则表达式来找到a标签，re:test是固定写法
        res = response.xpath(‘//a[re:test(@href, "/all/hot/recent/\d+")]/@href‘).extract()

        ‘‘‘

        md5_urls = set()
        for url in res:
            md5_url = self.md5(url)
            if md5_url in md5_urls:
                print(f"{url}--此url已存在")
            else:
                md5_urls.add(md5_url)
                print(url)

    def md5(self, url):
        import hashlib
        m = hashlib.md5()
        m.update(bytes(url, encoding="utf-8"))
        return m.hexdigest()

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request


class GetChoutiSpider(scrapy.Spider):
    name = ‘get_chouti‘
    allowed_domains = [‘chouti.com‘]
    start_urls = [‘https://dig.chouti.com/‘]
    # 当递归查找时，会反复执行parse，因此md5_urls不能定义在parse函数里面
    md5_urls = set()

    def parse(self, response):

        res = response.xpath(‘//div[@id="dig_lcpage"]//a/@href‘).extract()

        for url in res:
            md5_url = self.md5(url)
            if md5_url in self.md5_urls:
                pass
            else:
                print(url)
                self.md5_urls.add(md5_url)
                # 将新的要访问的url放到调度器
                url = "https://dig.chouti.com%s" % url
                yield Request(url=url, callback=self.parse)
        ‘‘‘
        /all/hot/recent/2
        /all/hot/recent/3
        /all/hot/recent/4
        /all/hot/recent/5
        /all/hot/recent/6
        /all/hot/recent/7
        /all/hot/recent/8
        /all/hot/recent/9
        /all/hot/recent/10
        /all/hot/recent/1
        /all/hot/recent/11
        /all/hot/recent/12
        ........
        ........
        ........
        /all/hot/recent/115
        /all/hot/recent/116
        /all/hot/recent/117
        /all/hot/recent/118
        /all/hot/recent/119
        /all/hot/recent/120

        ‘‘‘

    def md5(self, url):
        import hashlib
        m = hashlib.md5()
        m.update(bytes(url, encoding="utf-8"))
        return m.hexdigest()

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request


class GetChoutiSpider(scrapy.Spider):
    name = ‘get_chouti‘
    allowed_domains = [‘chouti.com‘]
    start_urls = [‘https://dig.chouti.com/‘]
    # 当递归查找时，会反复执行parse，因此md5_urls不能定义在parse函数里面
    md5_urls = set()

    def parse(self, response):

        res = response.xpath(‘//div[@id="dig_lcpage"]//a/@href‘).extract()

        for url in res:
            md5_url = self.md5(url)
            if md5_url in self.md5_urls:
                pass
            else:
                print(url)
                self.md5_urls.add(md5_url)
                # 将新的要访问的url放到调度器
                url = "https://dig.chouti.com%s" % url
                yield Request(url=url, callback=self.parse)
        ‘‘‘
        /all/hot/recent/2
        /all/hot/recent/3
        /all/hot/recent/4
        /all/hot/recent/5
        /all/hot/recent/6
        /all/hot/recent/7
        /all/hot/recent/8
        /all/hot/recent/9
        /all/hot/recent/10
        /all/hot/recent/1
        /all/hot/recent/11
        /all/hot/recent/12
        /all/hot/recent/13
        /all/hot/recent/14
        /all/hot/recent/15
        /all/hot/recent/16
        /all/hot/recent/17
        /all/hot/recent/18

        ‘‘‘

    def md5(self, url):
        import hashlib
        m = hashlib.md5()
        m.update(bytes(url, encoding="utf-8"))
        return m.hexdigest()