当我尝试添加以下代码时,它会给我一个错误
我安装了每个 python 模块,包括nltk
。我添加了lxml nampy
,但它不会起作用。我正在使用 python3 ,在这种情况下,我已将urllib2
更改为urllib.requests
。
请帮我找一个解决方案
我正在运行这个
python index.py
我的索引文件如下。 这是代码:
from bs4 import BeautifulSoup
from urllib.request import urlopen
import re
import ssl
import os
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
import codecs
def checkChar(token):
for char in token:
if(0 <= ord(char) and ord(char) <= 64) or (91 <= ord(char) and ord(char) <= 96) or (123 <= ord(char)):
return False
else:
continue
return True
def cleanMe(html):
soup = BeautifulSoup(html, "html.parser")
for script in soup(["script, style"]):
script.extract()
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
text = '\n'.join(chunk for chunk in chunks if chunk)
return text
path = 'crawled_html_pages/'
index = {}
docNum = 0
stop_words = set(stopwords.words('english'))
for filename in os.listdir(path):
collection = {}
docNum += 1
file = codecs.open('crawled_html_pages/' + filename, 'r', 'utf-8')
page_text = cleanMe(file)
tokens = nltk.word_tokenize(page_text)
filtered_sentence = [w for w in tokens if not w in stop_words]
filtered_sentence = []
breakWord = ''
for w in tokens:
if w not in stop_words:
filtered_sentence.append(w.lower())
for token in filtered_sentence:
if len(token) == 1 or token == 'and':
continue
if checkChar(token) == false:
continue
if token == 'giants':
breakWord = token
continue
if token == 'brady' and breakWord == 'giants':
break
if token not in collection:
collection[token] = 0
collection[token] += 1
for token in collection:
if tokennot in index:
index[token] = ''
index[token] = index[token] + '(' + str(docNum) + ', ' + str(collection[token]) + ")"
if docNum == 500:
print(index)
break
else:
continue
f = open('index.txt', 'w')
vocab = open('uniqueWords.txt', 'w')
for term in index:
f.write(term + ' =>' + index[term])
vocab.write(term + '\n')
f.write('\n')
f.close()
vocab.close()
print('Finished...')
这些是我得到的错误:
C:\ Users \ myworld&gt; python index.py
追溯(最近的呼叫最后):
文件&#34; index.py] [1]&#34;,第49行,在 page_text = cleanMe(文件)
文件&#34; index.py&#34;,第22行,在cleanMe中 汤= BeautifulSoup(html,&#34; html.parser&#34;)
文件&#34; C:\ Users \ furqa \ AppData \ Local \ Programs \ Python \ Python36-32 \ lib \ site-packages \ beautifulsoup4-4.6.0-py3.6.egg \ bs4__init __。py&#34;,line 191,在 init
中 文件&#34; C:\ Users \ furqa \ AppData \ Local \ Programs \ Python \ Python36-32 \ lib \ codecs.py&#34;,第700行,读取
return self.reader.read(size)
文件&#34; C:\ Users \ furqa \ AppData \ Local \ Programs \ Python \ Python36-32 \ lib \ codecs.py&#34;,第503行,读取
newchars,decodingbytes = self.decode(data,self.errors) UnicodeDecodeError:&#39; utf-8&#39;编解码器不能解码位置3131中的字节0x80: 起始字节无效
答案 0 :(得分:0)
您可以通过更改from_encoding参数来更改使用的BeautifulSoup编码类型:
汤= BeautifulSoup(html,from_encoding =“ iso-8859-8”)