Wiki API getter

Question

我知道还有其他类。我写这篇文章是因为我不需要所有的花哨，没有编辑，没有演讲等等，我只需要能够搜索标题并获得wiki标记。

任何建议、建议、评论、评论或任何真正的东西。

# -*- coding: utf-8 -*-

import urllib2
import re
import time
import sys
from urllib import quote_plus, _is_unicode

try:
    import json
except:
    import simplejson as json


def enum(*sequential, **named):
    enums = dict(zip(sequential, range(len(sequential))), **named)
    return type('Enum', (), enums)


class Wiki:
    def __init__(self, api=None):
        if api == None:
            self.api = "http://en.wikipedia.org/w/api.php"
        else:
            self.api = api
        return

    """A HTTP Request"""
    def downloadFile(self, URL=None):
        """     
        URL - The URL to fetch
        """
        opener = urllib2.build_opener()
        opener.addheaders = [('User-agent', 'Mozilla/5.0')]
        responce = opener.open(URL)
        data = responce.read()
        responce.close()
        return data.decode(encoding='UTF-8',errors='strict')


    """Search the wiki for titles"""
    def search(self, searchString):
        results = []
        if (searchString != u""):
            encoded_searchString = searchString
            if isinstance(encoded_searchString, unicode):
                encoded_searchString = searchString.encode('utf-8')
            url = self.api + "?action=query&list=search&format=json&srlimit=10&srsearch=" + urllib2.quote(encoded_searchString)
            rawData = self.downloadFile(url)
            object = json.loads(rawData)

            if object:
                if 'query' in object:
                    for item in object['query']['search']:
                        wikiTitle = item['title']
                        if isinstance(wikiTitle, str):
                            wikiTitle = wikiTitle.decode(encoding='UTF-8',errors='strict')
                        results.append(wikiTitle)
        return results


    """Search for the top wiki title"""
    def searchTop(self, searchString):
        results = self.search(searchString)
        if len(results) > 0:
            return results[0]
        else:
            return u""


    """Get the raw markup for a title"""
    def getPage(self, title):
        # Do the best we can to get a valid wiki title
        wikiTitle = self.searchTop(title)

        if (wikiTitle != u""):
            encoded_title = wikiTitle
            if isinstance(encoded_title, unicode):
                encoded_title = title.encode('utf-8')
            url = self.api + "?action=query&prop=revisions&format=json&rvprop=content&rvlimit=1&titles=" + urllib2.quote(encoded_title)
            rawData = self.downloadFile(url)
            object = json.loads(rawData)

            for k, v in object['query']['pages'].items():
                if 'revisions' in v:
                    return v['revisions'][0]['*']
        return u""

Answer 1

class Wiki:
    def __init__(self, api="http://en.wikipedia.org/w/api.php"):
        self.api = api
        return

这个返回没有任何作用。

    """A HTTP Request"""
    def downloadFile(self, URL=None):

Python约定是对方法名使用lowercase_with_underscores。

        """     
        URL - The URL to fetch
        """
        opener = urllib2.build_opener()
        opener.addheaders = [('User-agent', 'Mozilla/5.0')]

你为什么假装是Mozilla？

        responce = opener.open(URL)

反应拼写错误

        data = responce.read()
        responce.close()
        return data.decode(encoding='UTF-8',errors='strict')

整个函数应该是一个自由函数，而不是一个方法。

    """Search the wiki for titles"""
    def search(self, searchString):

参数按约定应命名为lowercase_with_underscore

        results = []
        if (searchString != u""):

不需要(和)。你也可以这么做：if searchString:

            encoded_searchString = searchString

为什么？

            if isinstance(encoded_searchString, unicode):
                encoded_searchString = searchString.encode('utf-8')
            url = self.api + "?action=query&list=search&format=json&srlimit=10&srsearch=" + urllib2.quote(encoded_searchString)
            rawData = self.downloadFile(url)
            object = json.loads(rawData)

我会把这两行结合起来

            if object:

在什么情况下，这将是虚假的？如果发生这种情况，你可能应该做些什么，除了假装什么都没有发生。

                if 'query' in object:
                    for item in object['query']['search']:
                        wikiTitle = item['title']
                        if isinstance(wikiTitle, str):
                            wikiTitle = wikiTitle.decode(encoding='UTF-8',errors='strict')
                        results.append(wikiTitle)
        return results


    """Search for the top wiki title"""
    def searchTop(self, searchString):
        results = self.search(searchString)
        if len(results) > 0:
            return results[0]
        else:
            return u""

如果没有找到结果，您真的想要空字符串吗？你应该在这里抛出一个例外。返回空字符串只会使故障难以跟踪。

    """Get the raw markup for a title"""
    def getPage(self, title):
        # Do the best we can to get a valid wiki title
        wikiTitle = self.searchTop(title)

        if (wikiTitle != u""):
            encoded_title = wikiTitle
            if isinstance(encoded_title, unicode):
                encoded_title = title.encode('utf-8')
            url = self.api + "?action=query&prop=revisions&format=json&rvprop=content&rvlimit=1&titles=" + urllib2.quote(encoded_title)
            rawData = self.downloadFile(url)
            object = json.loads(rawData)

            for k, v in object['query']['pages'].items():
                if 'revisions' in v:
                    return v['revisions'][0]['*']
        return u""

不要默认为愚蠢的缺省值。如果您无法获得请求的页面抛出一个错误尽可能多的细节，不要只是抛给我一个空字符串。

Answer 2

一个明显的跳到我面前的是：

class Wiki:
    def __init__(self, api=None):
        if api == None:
            self.api = "http://en.wikipedia.org/w/api.php"
        else:
            self.api = api
        return

可以简化为：

class Wiki:
    def __init__(self, api="http://en.wikipedia.org/w/api.php"):
        self.api = api