第五章 下载页面的所有src属性的文件p62

#!/usr/bin/env python
# _*_ coding:utf-8 _*_
import os
from urllib.request import urlopen, urlretrieve

from bs4 import BeautifulSoup

downloadDirectory="downloaded"
baseUrl="http://pyhtonscraping.com"
def getAbsoluteURL(baseUrl,source):
    if source.startswith("http://www."):
        url=source[11:]
    elif source.startswith("http://"):
        url=source
    elif source.startswith("www."):
        url="http://"+source[4:]
    else:
        url =baseUrl+"/"+source
    if baseUrl not in url:
        return None
    return url
def getDownloadPath(baseUrl,absoluteUrl,downloadDirectory):
    path=absoluteUrl.replace("www.","")
    path=path.replace(baseUrl,"")
    path=downloadDirectory+path
    directory= os.path.dirname(path)

    if not os.path.exists(directory):
        os.makedirs(directory)
    return  path
html=urlopen("http://www.pythonscraping.com")
bsObj=BeautifulSoup(html,"html.parser")
downloadLists=bsObj.findAll(src=True)
for download in downloadLists:
    fileUrl=getAbsoluteURL(baseUrl,download["src"])
    if fileUrl is not None:
        print(fileUrl)
        urlretrieve(fileUrl,getDownloadPath(baseUrl,fileUrl,downloadDirectory))