我想从网页上下载所有的文件。我尝试了wget，但它失败了，所以我决定使用Python路由，我找到了这个线程。

读完之后，我做了一个小的命令行应用程序，soupget，扩展了PabloG和Stan的优秀答案，并添加了一些有用的选项。

它使用BeatifulSoup收集页面的所有url，然后下载具有所需扩展名的url。最后，它可以同时下载多个文件。

下面就是:

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from __future__ import (division, absolute_import, print_function, unicode_literals)
import sys, os, argparse
from bs4 import BeautifulSoup

# --- insert Stan's script here ---
# if sys.version_info >= (3,): 
#...
#...
# def download_file(url, dest=None): 
#...
#...

# --- new stuff ---
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()

    # 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 multiprocessing.pool import ThreadPool
        results = ThreadPool(10).imap_unordered(
            lambda x: download_file(x, args.dest), all_links)
        for p in results:
            print(p)

它的用法示例如下:

python3 soupget.py -p -e <list of extensions> -d <destination_folder> -u <target_webpage>

还有一个实际的例子，如果你想看到它的作用:

python3 soupget.py -p -e .xlsx .pdf .csv -u https://healthdata.gov/dataset/chemicals-cosmetics

使用urllib.request.urlopen ():

import urllib.request
with urllib.request.urlopen('http://www.example.com/') as f:
    html = f.read().decode('utf-8')

这是使用库的最基本的方法，没有任何错误处理。您还可以执行更复杂的操作，例如更改头文件。

在Python 2中，该方法在urllib2中:

import urllib2
response = urllib2.urlopen('http://www.example.com/')
html = response.read()

如果你安装了wget，你可以使用parallel_sync。

PIP安装parallel_sync

from parallel_sync import wget
urls = ['http://something.png', 'http://somthing.tar.gz', 'http://somthing.zip']
wget.download('/tmp', urls)
# or a single file:
wget.download('/tmp', urls[0], filenames='x.zip', extract=True)

道格: https://pythonhosted.org/parallel_sync/pages/examples.html

这是非常强大的。它可以并行下载文件，失败时重试，甚至可以在远程机器上下载文件。

import os,requests
def download(url):
    get_response = requests.get(url,stream=True)
    file_name  = url.split("/")[-1]
    with open(file_name, 'wb') as f:
        for chunk in get_response.iter_content(chunk_size=1024):
            if chunk: # filter out keep-alive new chunks
                f.write(chunk)


download("https://example.com/example.jpg")

Urlretrieve和请求。得到的都很简单，然而现实却不。 我已经为两个站点提取了数据，包括文本和图像，以上两个可能解决了大部分任务。但如果想要更通用的解决方案，我建议使用urlopen。由于它包含在Python 3标准库中，您的代码可以在任何运行Python 3的机器上运行，而无需预先安装site-package

import urllib.request
url_request = urllib.request.Request(url, headers=headers)
url_connect = urllib.request.urlopen(url_request)

#remember to open file in bytes mode
with open(filename, 'wb') as f:
    while True:
        buffer = url_connect.read(buffer_size)
        if not buffer: break

        #an integer value of size of written data
        data_wrote = f.write(buffer)

#you could probably use with-open-as manner
url_connect.close()

当使用Python通过HTTP下载文件时，这个答案提供了HTTP 403禁止的解决方案。我只尝试了请求和urllib模块，其他模块可能会提供更好的东西，但这是我用来解决大多数问题的一个。

我写了下面的代码，它可以在普通的Python 2或Python 3中工作。

import sys
try:
    import urllib.request
    python3 = True
except ImportError:
    import urllib2
    python3 = False


def progress_callback_simple(downloaded,total):
    sys.stdout.write(
        "\r" +
        (len(str(total))-len(str(downloaded)))*" " + str(downloaded) + "/%d"%total +
        " [%3.2f%%]"%(100.0*float(downloaded)/float(total))
    )
    sys.stdout.flush()

def download(srcurl, dstfilepath, progress_callback=None, block_size=8192):
    def _download_helper(response, out_file, file_size):
        if progress_callback!=None: progress_callback(0,file_size)
        if block_size == None:
            buffer = response.read()
            out_file.write(buffer)

            if progress_callback!=None: progress_callback(file_size,file_size)
        else:
            file_size_dl = 0
            while True:
                buffer = response.read(block_size)
                if not buffer: break

                file_size_dl += len(buffer)
                out_file.write(buffer)

                if progress_callback!=None: progress_callback(file_size_dl,file_size)
    with open(dstfilepath,"wb") as out_file:
        if python3:
            with urllib.request.urlopen(srcurl) as response:
                file_size = int(response.getheader("Content-Length"))
                _download_helper(response,out_file,file_size)
        else:
            response = urllib2.urlopen(srcurl)
            meta = response.info()
            file_size = int(meta.getheaders("Content-Length")[0])
            _download_helper(response,out_file,file_size)

import traceback
try:
    download(
        "https://geometrian.com/data/programming/projects/glLib/glLib%20Reloaded%200.5.9/0.5.9.zip",
        "output.zip",
        progress_callback_simple
    )
except:
    traceback.print_exc()
    input()

注:

支持“进度条”回调。 从我的网站上下载一个4 MB的测试包。zip。