scripy爬取页面并按目录结构存放页面

http://www.w3c.com.cn/scripy%E7%88%AC%E5%8F%96%E9%A1%B5%E9%9D%A2%E5%B9%B6%E6%8C%89%E7%9B%AE%E5%BD%95%E7%BB%93%E6%9E%84%E5%AD%98%E6%94%BE%E9%A1%B5%E9%9D%A2

0.00 / 5 5 1 / 5 2 / 5 3 / 5 4 / 5 5 / 5 0 votes,  0.00 avg. rating ( 0% score) 给大家共享一段代码，希望对发家有帮助。 该代码的作用是将指定站点的页面递归的爬取，并按照目录结构存放爬取结果： from scrapy.selector import HtmlXPathSelector from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor from scrapy.contrib.spiders import CrawlSpider, Rule from scrapy.http import Request from scrapy import log import os, os.path class BookSpider(CrawlSpider): name = 'Book' #allowed_domains = ['xx.com'] #start_urls = ['http://www.xx.com/'] #rules = ( # Rule(SgmlLinkExtractor(allow=r'\.html'), callback='parse_item', follow=True), #) def __init__(self, start_url, output_dir = "./", *args, **kwargs): super(BookSpider, self).__init__(*args, **kwargs) self.start_urls = [] self.start_urls.append(start_url) self.output_dir = output_dir self.allowed_domains = map(self._get_domain, self.start_urls) def _get_domain(self, url): first_dot = url.find('.') if -1 == first_dot: return None first_slash = url.find('/', first_dot + 1) if -1 == first_slash: return url[first_dot + 1:] return url[first_dot + 1: first_slash] def parse(self, response): """first Request return to fetch start_url""" self.parse_detail(response) yield Request(response.url, callback = self.parse_item) def parse_item(self, response): page_links = SgmlLinkExtractor(allow=r'\.html').extract_links(response) """ iterate two times for BFS; one for DFS""" for link in page_links: yield Request(link.url, callback = self.parse_detail) for link in page_links: yield Request(link.url, callback = self.parse_item) def parse_detail(self, response): outputfile = self._rtouch(response.url) if not outputfile: log.msg("download %s fail" % response.url, level = log.WARNING, spider = self) return with open(outputfile, 'w') as f: f.write(response.body) log.msg("download file: %s" % outputfile, level = log.INFO, spider = self) def _rtouch(self, filepath): pos = filepath.find('://') if -1 != pos: filepath = filepath[pos + 3:] if ".html" != filepath[-5:]: filepath += "/index.html" opath = os.path.abspath(self.output_dir + "/" + filepath) basedir = os.path.dirname(opath) if not os.path.exists(basedir): try: os.makedirs(basedir) except Exception, msg: log.msg(msg, level = log.WARNING, spider = self) return None return opath