UnicodeDecodeError:“ascii”编解码器无法解码位置4中的字节0xe2：序号不在范围内（128）

Question

我从https://github.com/davidadamojr/TextRank获取了这段代码，我正面临这个问题。我试图通过将utf-8放入“keyphrases=decode（'utf-8'）。extractKeyphrases（text）”来解决，但失败了。在

代码如下：

"""
From this paper: http://acl.ldc.upenn.edu/acl2004/emnlp/pdf/Mihalcea.pdf 

External dependencies: nltk, numpy, networkx

Based on https://gist.github.com/voidfiles/1646117
"""

import nltk
import itertools
from operator import itemgetter
import networkx as nx
import sys
import os

#apply syntactic filters based on POS tags
def filter_for_tags(tagged, tags=['NN', 'JJ', 'NNP']):
    return [item for item in tagged if item[1] in tags]

def normalize(tagged):
    return [(item[0].replace('.', ''), item[1]) for item in tagged]

def unique_everseen(iterable, key=None):
    "List unique elements, preserving order. Remember all elements ever seen."
    # unique_everseen('AAAABBBCCDAABBB') --> A B C D
    # unique_everseen('ABBCcAD', str.lower) --> A B C D
    seen = set()
    seen_add = seen.add
    if key is None:
        for element in itertools.ifilterfalse(seen.__contains__, iterable):
            seen_add(element)
            yield element
    else:
        for element in iterable:
            k = key(element)
            if k not in seen:
                seen_add(k)
                yield element

def lDistance(firstString, secondString):
    "Function to find the Levenshtein distance between two words/sentences - gotten from http://rosettacode.org/wiki/Levenshtein_distance#Python"
    if len(firstString) > len(secondString):
        firstString, secondString = secondString, firstString
    distances = range(len(firstString) + 1)
    for index2, char2 in enumerate(secondString):
        newDistances = [index2 + 1]
        for index1, char1 in enumerate(firstString):
            if char1 == char2:
                newDistances.append(distances[index1])
            else:
                newDistances.append(1 + min((distances[index1], distances[index1+1], newDistances[-1])))
        distances = newDistances
    return distances[-1]

def buildGraph(nodes):
    "nodes - list of hashables that represents the nodes of the graph"
    gr = nx.Graph() #initialize an undirected graph
    gr.add_nodes_from(nodes)
    nodePairs = list(itertools.combinations(nodes, 2))

    #add edges to the graph (weighted by Levenshtein distance)
    for pair in nodePairs:
        firstString = pair[0]
        secondString = pair[1]
        levDistance = lDistance(firstString, secondString)
        gr.add_edge(firstString, secondString, weight=levDistance)

    return gr

def extractKeyphrases(text):
    #tokenize the text using nltk
    wordTokens = nltk.word_tokenize(text)

    #assign POS tags to the words in the text
    tagged = nltk.pos_tag(wordTokens)
    textlist = [x[0] for x in tagged]

    tagged = filter_for_tags(tagged)
    tagged = normalize(tagged)

    unique_word_set = unique_everseen([x[0] for x in tagged])
    word_set_list = list(unique_word_set)

   #this will be used to determine adjacent words in order to construct keyphrases with two words

    graph = buildGraph(word_set_list)

    #pageRank - initial value of 1.0, error tolerance of 0,0001, 
    calculated_page_rank = nx.pagerank(graph, weight='weight')

    #most important words in ascending order of importance
    keyphrases = sorted(calculated_page_rank, key=calculated_page_rank.get, reverse=True)

    #the number of keyphrases returned will be relative to the size of the text (a third of the number of vertices)
    aThird = len(word_set_list) / 3
    keyphrases = keyphrases[0:aThird+1]

    #take keyphrases with multiple words into consideration as done in the paper - if two words are adjacent in the text and are selected as keywords, join them
    #together
    modifiedKeyphrases = set([])
    dealtWith = set([]) #keeps track of individual keywords that have been joined to form a keyphrase
    i = 0
    j = 1
    while j < len(textlist):
        firstWord = textlist[i]
        secondWord = textlist[j]
        if firstWord in keyphrases and secondWord in keyphrases:
            keyphrase = firstWord + ' ' + secondWord
            modifiedKeyphrases.add(keyphrase)
            dealtWith.add(firstWord)
            dealtWith.add(secondWord)
        else:
            if firstWord in keyphrases and firstWord not in dealtWith: 
                modifiedKeyphrases.add(firstWord)

            #if this is the last word in the text, and it is a keyword,
            #it definitely has no chance of being a keyphrase at this point    
            if j == len(textlist)-1 and secondWord in keyphrases and secondWord not in dealtWith:
                modifiedKeyphrases.add(secondWord)

        i = i + 1
        j = j + 1

    return modifiedKeyphrases

def extractSentences(text):
    sent_detector = nltk.data.load('tokenizers/punkt/english.pickle')
    sentenceTokens = sent_detector.tokenize(text.strip())
    graph = buildGraph(sentenceTokens)

    calculated_page_rank = nx.pagerank(graph, weight='weight')

    #most important sentences in ascending order of importance
    sentences = sorted(calculated_page_rank, key=calculated_page_rank.get, reverse=True)

    #return a 100 word summary
    summary = ' '.join(sentences)
    summaryWords = summary.split()
    summaryWords = summaryWords[0:101]
    summary = ' '.join(summaryWords)

    return summary

def writeFiles(summary, keyphrases, fileName):
    "outputs the keyphrases and summaries to appropriate files"
    print "Generating output to " + 'keywords/' + fileName
    keyphraseFile = open('keywords/' + fileName, 'w')
    for keyphrase in keyphrases:
        keyphraseFile.write(keyphrase + '\n')
    keyphraseFile.close()

    print "Generating output to " + 'summaries/' + fileName
    summaryFile = open('summaries/' + fileName, 'w')
    summaryFile.write(summary)
    summaryFile.close()

    print "-"


#retrieve each of the articles
articles = os.listdir("articles")
for article in articles:
    print 'Reading articles/' + article
    articleFile = open('articles/' + article, 'r')
    text = articleFile.read()
    keyphrases = decode('utf-8').extractKeyphrases(text)
    summary = extractSentences(text)
    writeFiles(summary, keyphrases, article)

错误：

^{pr2}$

有什么想法吗？（抱歉英语不好）

Answer 1

我想你想要的是：

# ...
text = articleFile.read().decode('utf-8')
keyphrases = extractKeyphrases(text)
# ...

基本上，您希望在阅读文件时立即将其内容解码为unicode字符串。然后程序的其余部分就可以避免转换问题了。还请确保文件实际上是utf-8编码。如果不确定，请尝试将latin1作为编码，因为这样在解码时永远不会引发异常（当然，当文件不是latin1编码时，仍然会生成错误的文本）