python - 阅读级脚本在某些站点上发送错误“IndexError:字符串索引超出范围”

在这里完成初学者。以下代码旨在分析网站中的p标签（使用Python）并显示该网站的阅读水平。

#import both BS4 and the new URLLIB using the added .request
from urllib.request import urlopen as uReq
from bs4 import BeautifulSoup as soup

#credit to AbigailB (https://stackoverflow.com/users/1798848/abigailb)
def syllables(word):
    count = 0
    vowels = 'aeiouy'
    word = word.lower().strip(".:;?!")
    if word[0] in vowels:
        count += 1
    for index in range(1,len(word)):
        if word[index] in vowels and word[index-1] not in vowels:
            count += 1
    if word.endswith('e'):
        count -= 1
    if word.endswith('le'):
        count+=1
    if count == 0:
        count += 1
    return count

#site prompt, to be replaced by active tab browser address
#site = input("Enter the website to find out its reading level:")
#my_url = "{}".format(site)

#default site for testing
my_url = "https://en.wikipedia.org/wiki/Jane_Austen"

uClient = uReq(my_url)
page_html = uClient.read()
uClient.close()

#empty variables to be pushed w/ extracted, looped text
senNum = []
wordNum = []
syllNum = []

page_soup = soup(page_html, "html.parser")
page_soup.findAll("p")
paragraphs = page_soup.findAll("p")

#loop through every paragraph, do magic
for para in paragraphs:
    para = para.text.strip()
    paraSen = int(len(para.split('.')) - 1)
    paraWord = int(len(para.split()))
    paraSyll = syllables(para)
    intParaSen = int(paraSen)
    intParaWord = int(paraWord)
    intParaSyll = int(paraSyll)

    #append stripped values into empty variables
    senNum.append(intParaSen)
    wordNum.append(intParaWord)
    syllNum.append(intParaSyll)

#sums of all previously empty values
sumSenNum = sum(senNum)
sumWordNum = sum(wordNum)
sumSyllNum = sum(syllNum)

#averages for Flesch–Kincaid ease
avgWordsPerSen = sumWordNum/sumSenNum
avgSyllPerWord = sumSyllNum/sumWordNum

#final parts for Flesch–Kincaid ease
calcOne = avgWordsPerSen * 0.39
calcTwo = avgSyllPerWord * 11.8
finalCalc = calcOne + calcTwo - 15.59

print(finalCalc)

它在很大程度上取决于我在上面发现的标为def syllables（word）的代码块（在上面找到了贷项），该代码显示字符串中的音节数。它在某些站点上有效，但是在其他站点上运行代码时，出现以下错误：

Traceback (most recent call last):
  File "C:\Users\Waves\Desktop\gradeLevel.py", line 48, in <module>
    paraSyll = syllables(para)
  File "C:\Users\Waves\Desktop\gradeLevel.py", line 10, in syllables
    if word[0] in vowels:
IndexError: string index out of range

据我了解，它可能与[0]是数组中的第一个对象有关，而我相信原始作者的意思是暗示“如果没有元音分隔符...”，但我不确定。请随意与您对代码的任何无关的评论。先感谢您！

最佳答案

p元素中有空文本

for para in paragraphs:
    print(para)
    # <p class="mw-empty-elt">   </p>

只是跳过那个

for para in paragraphs:
    para = para.text.strip()
    if not para:
        continue