Created
February 26, 2012 13:21
-
-
Save ksamuel/1916685 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
# vim: ai ts=4 sts=4 et sw=4 nu | |
import urlparse | |
import os | |
import urllib | |
from scrapy.utils.url import urljoin_rfc | |
from scrapy.selector import HtmlXPathSelector | |
from scrapy.utils.response import get_base_url | |
from scrapy.contrib.spiders import CrawlSpider, Rule | |
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor | |
BIBLIO = "/home/kevin/Bureau/livres/biblio" | |
os.environ['DOWNLOAD_DELAY'] = "0.25" | |
os.environ['USER_AGENT'] = "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.A.B.C Safari/525.13" | |
class BooksSpider(CrawlSpider): | |
name = "books" | |
allowed_domains = ["dl.dropbox.com"] | |
start_urls = [ | |
"http://dl.dropbox.com/u/25833073/Boudu/_catalog/82267917/82267917_books.html", | |
] | |
rules = ( | |
Rule(SgmlLinkExtractor(allow=(r'.*_books_.*\.html', ) )), | |
Rule(SgmlLinkExtractor(allow=(r'book_.*\.html', )), callback='parse'), | |
) | |
def parse(self, response): | |
hxs = HtmlXPathSelector(response) | |
base_url = get_base_url(response) | |
urls = hxs.select("//*[contains(text(), 'Télécharger')]/@href") | |
urls = (urljoin_rfc(base_url, url) for url in urls.extract()) | |
for url in urls: | |
filename = urlparse.unquote(url).split('/')[-1] | |
try: | |
urllib.urlretrieve(url, os.path.join(BIBLIO, filename)) | |
except Exception as e: | |
print e |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment