05存储数据

Python3中，urllib.request.urlretrieve根据文件的URL下载文件。

程序从http://pythonscraping.com下载logo图片，然后在程序运行的文件夹里保存为logo.jpg文件。

from urllib.request import urlretrieve
from urllib.request import urlopen
from bs4 import BeautifulSoup

html = urlopen("http://pythonscraping.com")
bsObj = BeautifulSoup(html)
imageLocation = bsObj.find("a", {"id":"logo"}).find("img")["src"]
urlretrieve(imageLocation, "logo.jpg")

程序把http://pythonscraping.com上所有src属性的文件都下载：

import os
from urllib.request import urlretrieve
from urllib.request import urlopen
from bs4 import BeautifulSoup

downloadDirectory = "downloaded"
baseUrl = "http://pythonscraping.com"

def getAbsoluteURL(baseUrl, source):
    if source.startswith("http://www."):
        url = "http://" + 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

del 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://pythonscraping.com")
bsObj = BeautifulSoup(html)
downloadList = bsObj.findAll(src=True)

for download in downloadList:
    fileUrl = getAbsoluteURL(baseUrl, download["src"])
    if fileUrl is not None:
        print(fileUrl)
        urlretrieve(fileUrl, getDownloadPath(baseUrl, fileUrl, downloadDirectory))