我们在写普通脚本的时候,从一个网站拿到一个文件的下载url,然后下载,直接将数据写入文件或者保存下来,但是这个需要我们自己一点一点的写出来,而且反复利用率并不高,为了不重复造轮子,scrapy提供很流畅的下载文件方式,只需要随便写写便可用了。
mat.py文件
1 # -*- coding: utf-8 -*-
2 import scrapy
3 from scrapy.linkextractor import LinkExtractor
4 from weidashang.items import matplotlib
5
6 class MatSpider(scrapy.Spider):
7 name = "mat"
8 allowed_domains = ["matplotlib.org"]
9 start_urls = ['https://matplotlib.org/examples']
10
11 def parse(self, response):
#抓取每个脚本文件的访问页面,拿到后下载
12 link = LinkExtractor(restrict_css='div.toctree-wrapper.compound li.toctree-l2')
13 for link in link.extract_links(response):
14 yield scrapy.Request(url=link.url,callback=self.example)
15
16 def example(self,response):
#进入每个脚本的页面,抓取源码文件按钮,并和base_url结合起来形成一个完整的url
17 href = response.css('a.reference.external::attr(href)').extract_first()
18 url = response.urljoin(href)
19 example = matplotlib()
20 example['file_urls'] = [url]
21 return example
pipelines.py
1 class MyFilePlipeline(FilesPipeline):
2 def file_path(self, request, response=None, info=None):
3 path = urlparse(request.url).path
4 return join(basename(dirname(path)),basename(path))
settings.py
1 ITEM_PIPELINES = {
2 'weidashang.pipelines.MyFilePlipeline': 1,
3 }
4 FILES_STORE = 'examples_src'
items.py
class matplotlib(Item):
file_urls = Field()
files = Field()
run.py
1 from scrapy.cmdline import execute
2 execute(['scrapy', 'crawl', 'mat','-o','example.json'])