Python-Wikipedia Automated Downloader

时间:2011-03-11 21:20:47

标签: python download python-3.x wikipedia pywikibot

[使用Python 3.1]有没有人知道如何让Python 3应用程序允许用户编写一个文本文件,其中多个单词用逗号分隔。程序应该读取文件,并下载所请求项目的维基百科页面。例如如果他们输入hello,python-3,鸡会去维基百科并下载http://www.wikipedia.com/wiki/hellohttp://www.wikip ......有人认为他们可以这样做吗?

当我说“下载”时,我的意思是下载文本,与图像无关。

3 个答案:

答案 0 :(得分:1)

您确切地描述了如何制作这样的节目。那么问题是什么?

您阅读文件,用逗号分隔,然后下载网址。完成!

答案 1 :(得分:1)

查找urllib.request

答案 2 :(得分:0)

检查以下代码,它下载html,没有图像,但您可以从正在解析的xml文件中访问它们以获取URL。

from time import sleep
import urllib
import urllib2
from xml.dom import minidom, Node

def main():
    print "Hello World"

    keywords = []

    key_file = open("example.txt", 'r')
    if key_file:
        temp_lines = key_file.readlines()

        for keyword_line in temp_lines:
            keywords.append(keyword_line.rstrip("\n"))

        key_file.close()

    print "Total keywords: %d" % len(keywords)
    for keyword in keywords:
        url = "http://en.wikipedia.org/w/api.php?format=xml&action=opensearch&search=" + keyword
        xmldoc = minidom.parse(urllib.urlopen(url))
        root_node = xmldoc.childNodes[0]

        section_node = None
        for node in root_node.childNodes:
            if node.nodeType == Node.ELEMENT_NODE and \
            node.nodeName == "Section":
                section_node = node
                break

        if section_node is not None:
            items = []
            for node in section_node.childNodes:
                if node.nodeType == Node.ELEMENT_NODE and \
                node.nodeName == "Item":
                    items.append(node)

            if len(items) == 0:
                print "NO results found"
            else:
                print "\nResults found for " + keyword + ":\n"
                for item in items:
                    for node in item.childNodes:
                        if node.nodeType == Node.ELEMENT_NODE and \
                        node.nodeName == "Text":
                            if len(node.childNodes) == 1:
                                print node.childNodes[0].data.encode('utf-8')

                file_name = None
                for node in items[0].childNodes:
                    if node.nodeType == Node.ELEMENT_NODE and \
                    node.nodeName == "Text":
                        if len(node.childNodes) == 1:
                            file_name = "Html\%s.html" % node.childNodes[0].data.encode('utf-8')
                            break

                if file_name is not None:
                    file = open(file_name, 'w')
                    if file:
                        for node in items[0].childNodes:
                            if node.nodeType == Node.ELEMENT_NODE and \
                            node.nodeName == "Url":
                                if len(node.childNodes) == 1:
                                    user_agent = 'Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 6.0)'
                                    header = { 'User-Agent' : user_agent }
                                    request = urllib2.Request(url=node.childNodes[0].data, headers=header)
                                    file.write(urllib2.urlopen(request).read())
                                    file.close()
                                    break


    print "Sleeping"
    sleep(2)

if __name__ == "__main__":
    main()