如何使用Python脚本下载完整的网页？

Question

目前，我有一个只能下载HTML给定页面的脚本。

现在我想 下载网页中的所有文件 ，包括HTML，CSS，JS和 图像文件 （同我们得到任何网站的CTRL-S）。

我当前的代码是：

import urllib
url = "https://en.wikipedia.org/wiki/Python_%28programming_language%29"
urllib.urlretrieve(url, "t3.html")

我访问了许多问题，但它们都只下载了HTML。

Answer 1

以下实现使您能够获取HTML子网站。为了获得您需要的其他文件，可以对其进行更完善的开发。我depth为您设置了变量，以设置要解析的最大sub_websites。

import urllib2
from BeautifulSoup import *
from urlparse import urljoin


def crawl(pages, depth=None):
    indexed_url = [] # a list for the main and sub-HTML websites in the main website
    for i in range(depth):
        for page in pages:
            if page not in indexed_url:
                indexed_url.append(page)
                try:
                    c = urllib2.urlopen(page)
                except:
                    print "Could not open %s" % page
                    continue
                soup = BeautifulSoup(c.read())
                links = soup('a') #finding all the sub_links
                for link in links:
                    if 'href' in dict(link.attrs):
                        url = urljoin(page, link['href'])
                        if url.find("'") != -1:
                                continue
                        url = url.split('#')[0] 
                        if url[0:4] == 'http':
                                indexed_url.append(url)
        pages = indexed_url
    return indexed_url


pagelist=["https://en.wikipedia.org/wiki/Python_%28programming_language%29"]
urls = crawl(pagelist, depth=2)
print urls

Python3版本，2019年。这可以节省一些时间：

#!/usr/bin/env python


import urllib.request as urllib2
from bs4 import *
from urllib.parse  import urljoin


def crawl(pages, depth=None):
    indexed_url = [] # a list for the main and sub-HTML websites in the main website
    for i in range(depth):
        for page in pages:
            if page not in indexed_url:
                indexed_url.append(page)
                try:
                    c = urllib2.urlopen(page)
                except:
                    print( "Could not open %s" % page)
                    continue
                soup = BeautifulSoup(c.read())
                links = soup('a') #finding all the sub_links
                for link in links:
                    if 'href' in dict(link.attrs):
                        url = urljoin(page, link['href'])
                        if url.find("'") != -1:
                                continue
                        url = url.split('#')[0] 
                        if url[0:4] == 'http':
                                indexed_url.append(url)
        pages = indexed_url
    return indexed_url


pagelist=["https://en.wikipedia.org/wiki/Python_%28programming_language%29"]
urls = crawl(pagelist, depth=1)
print( urls )