Skip to content

Instantly share code, notes, and snippets.

@gibbbone

gibbbone/soupget.py

Last active Jun 6, 2020
Embed
What would you like to do?
How to download all files with certain extensions from the same webpage with Python
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from __future__ import (division, absolute_import, print_function, unicode_literals)
import sys, os, argparse, time
from bs4 import BeautifulSoup
# from: https://stackoverflow.com/a/16518224/6332373
if sys.version_info >= (3,):
import urllib.request as urllib2
import urllib.parse as urlparse
else:
import urllib2
import urlparse
def download_file(url, dest=None):
"""
Download and save a file specified by url to dest directory,
"""
u = urllib2.urlopen(url)
scheme, netloc, path, query, fragment = urlparse.urlsplit(url)
filename = os.path.basename(path)
if not filename:
filename = 'downloaded.file'
if dest:
filename = os.path.join(dest, filename)
with open(filename, 'wb') as f:
meta = u.info()
meta_func = meta.getheaders if hasattr(meta, 'getheaders') else meta.get_all
meta_length = meta_func("Content-Length")
file_size = None
if meta_length:
file_size = int(meta_length[0])
print("Downloading: {0} Bytes: {1}".format(url, file_size))
file_size_dl = 0
block_sz = 8192
while True:
buffer = u.read(block_sz)
if not buffer:
break
file_size_dl += len(buffer)
f.write(buffer)
status = "{0:16}".format(file_size_dl)
if file_size:
status += " [{0:6.2f}%]".format(file_size_dl * 100 / file_size)
status += chr(13)
print(status, end="")
print()
return filename
def collect_all_url(page_url, extensions):
"""
Recovers all links in page_url checking for all the desired extensions
"""
conn = urllib2.urlopen(page_url)
html = conn.read()
soup = BeautifulSoup(html, 'lxml')
links = soup.find_all('a')
results = []
for tag in links:
link = tag.get('href', None)
if link is not None:
for e in extensions:
if e in link:
# Fallback for badly defined links
# checks for missing scheme or netloc
if bool(urlparse.urlparse(link).scheme) and bool(urlparse.urlparse(link).netloc):
results.append(link)
else:
new_url=urlparse.urljoin(page_url,link)
results.append(new_url)
return results
if __name__ == "__main__": # Only run if this file is called directly
# Command line arguments
parser = argparse.ArgumentParser(
description='Download all files from a webpage.')
parser.add_argument(
'-u', '--url',
help='Page url to request')
parser.add_argument(
'-e', '--ext',
nargs='+',
help='Extension(s) to find')
parser.add_argument(
'-d', '--dest',
default=None,
help='Destination where to save the files')
parser.add_argument(
'-p', '--par',
action='store_true', default=False,
help="Turns on parallel download")
args = parser.parse_args()
t1 = time.time()
# Recover files to download
all_links = collect_all_url(args.url, args.ext)
# Download
if not args.par:
for l in all_links:
try:
filename = download_file(l, args.dest)
print(l)
except Exception as e:
print("Error while downloading: {}".format(e))
else:
# from: https://markhneedham.com/blog/2018/07/15/python-parallel-download-files-requests/
from multiprocessing.pool import ThreadPool
results = ThreadPool(10).imap_unordered(
lambda x: download_file(x, args.dest), all_links)
for p in results:
print(p)
t2 = time.time()
print("Elapsed time: {}".format(t2-t1))
@gibbbone

This comment has been minimized.

Copy link
Owner Author

@gibbbone gibbbone commented Mar 6, 2020

Try it:

python3 soupget.py -p -e .xlsx .pdf .csv -u https://healthdata.gov/dataset/chemicals-cosmetics
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.