python使用scrapy爬取妹子图

python scrapy爬虫,听说妹子图挺火,我整站爬取了,上周一共搞了大概8000多张图片。和大家分享一下。

核心爬虫代码

# -*- coding: utf-8 -*-
from scrapy.selector import selector
import scrapy
from scrapy.contrib.loader import itemloader, identity
from 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(“//p[@]/p[@]/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’, “//p[@]/p[@]/p[@]/p”)
l.add_xpath(‘image_urls’, “//p[@]/p/img/@src”, identity())
l.add_value(‘url’, response.url)
return l.load_item()

项目地址:https://github.com/zhangbohan/fun_crawler

以上所述就是本文的全部内容了,希望大家能够喜欢。

Posted in 未分类