Python使用Scrapy爬取妹子圖

Python Scrapy爬蟲，聽說妹子圖挺火，我整站爬取了，上周一共搞了大概8000多張圖片。和大家分享一下。

核心爬蟲代碼

# -*- coding: utf-8 -*-from scrapy.selector import Selectorimport scrapyfrom scrapy.contrib.loader import ItemLoader, Identityfrom fun.items import MeizituItem  class MeizituSpider(scrapy.Spider):  name = "meizitu"  allowed_domains = ["meizitu.com"]  start_urls = (    'http://www.meizitu.com/',  )   def parse(self, response):    sel = Selector(response)    for link in sel.xpath('//h2/a/@href').extract():      request = scrapy.Request(link, callback=self.parse_item)      yield request     pages = sel.xpath("//div[@class='navigation']/div[@id='wp_page_numbers']/ul/li/a/@href").extract()    print('pages: %s' % pages)    if len(pages) > 2:      page_link = pages[-2]      page_link = page_link.replace('/a/', '')        request = scrapy.Request('http://www.meizitu.com/a/%s' % page_link, callback=self.parse)      yield request   def parse_item(self, response):    l = ItemLoader(item=MeizituItem(), response=response)    l.add_xpath('name', '//h2/a/text()')    l.add_xpath('tags', "//div[@id='maincontent']/div[@class='postmeta clearfix']/div[@class='metaRight']/p")    l.add_xpath('image_urls', "//div[@id='picture']/p/img/@src", Identity())     l.add_value('url', response.url)    return l.load_item()

項目地址：https://github.com/ZhangBohan/fun_crawler

以上所述就是本文的全部內容了，希望大家能夠喜歡。

