Created
February 26, 2011 21:09
-
-
Save jharjono/845627 to your computer and use it in GitHub Desktop.
Downloads all files of a certain file format on a web page to local filesystem
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 | |
# Downloads all files of a certain file format on a web page to local filesystem | |
import urllib2 | |
import lxml | |
import os | |
from lxml.html import fromstring | |
from urlparse import urljoin | |
from urllib import urlretrieve | |
class Downloader(object): | |
def __init__(self, url, output_dir, doctype): | |
self.url = url | |
self.page = urllib2.urlopen(self.url).read() | |
self.search_tree = fromstring(self.page) | |
self.output_dir = output_dir | |
self.doctype = doctype | |
def start(self): | |
links = self._get_doc_links(self.doctype) | |
for f in links: | |
self.download(f) | |
def _get_doc_links(self, doctype): | |
""" | |
Helper method to obtain all links of a certain doctype in ``self.url`` | |
""" | |
pdf_links = [] | |
# Ensure document type is a file extension | |
if not doctype.startswith("."): | |
doctype = "." + doctype | |
for a in self.search_tree.cssselect('a'): | |
href = a.get('href') | |
if href and href.endswith(doctype): | |
# We only need the last part of the URL | |
pdf_fname = href.split('/')[-1] | |
pdf_links.append(pdf_fname) | |
return pdf_links | |
def download(self, link): | |
""" | |
Does actual downloading to filesystem | |
""" | |
file_url = urljoin(self.url, link) | |
file_name = os.path.join(self.output_dir, link) | |
print "Downloading file %s to %s" %(file_url, file_name) | |
urlretrieve(file_url, file_name) | |
if __name__ == "__main__": | |
import argparse | |
parser = argparse.ArgumentParser(description="Downloads all documents of specific file format in a webpage") | |
parser.add_argument("-u", "--url", metavar="url", | |
help="the URL of the webpage", required=True, dest="url") | |
parser.add_argument("-t", "--type", metavar="type", | |
help="document type", required=True, dest="type") | |
parser.add_argument("-o", "--output-dir", metavar="output_dir", | |
help="output directory for all the scraped files, defaults to cwd", required=False, dest="output_dir") | |
args = parser.parse_args() | |
url = args.url | |
output_dir = args.output_dir if args.output_dir else os.getcwd() | |
doctype = args.type | |
downloader = Downloader(url, output_dir, doctype) | |
downloader.start() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment