Python:索引超出范围E

Question

下面的代码不断地在print (aTweet + '~' + timeSource[x] + '~' + keyWord[i])行上给出错误IndexError: list index out of range。这和keyword[i]术语有关吗？我理解Index out of range通常意味着提供一个列表元素不存在的索引。这是否意味着错误实际上可能存在于本节中：

   if ( len(splitSource) > 20 ):
                max_range = 19
            else:
                max_range = len(splitSource)

参考代码：

import re
from re import sub
import time
import cookielib
from cookielib import CookieJar
import urllib2
from urllib2 import urlopen
import difflib
import sys

cj = CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
opener.addheaders = [('User-agent', 'Mozilla/5.0')]

keyWord = ["Scotch"]

def main():
    i=0
    while i<len(keyWord):
        startingLink = 'https://twitter.com/search/realtime?q='+keyWord[i]
        tUrl = startingLink+'&src=hash'

        oldTwit = []
        newTwit = []


        howSimAr = [.5,.5,.5,.5,.5]

        sourceCode = opener.open(tUrl).read()  
        splitSource = re.findall(r'<p class="js-tweet-text tweet-text">(.*?)</p>',sourceCode)
        timeSource = re.findall(r'js-nav" title="(.*?)"',sourceCode)

        if ( len(splitSource) > 20 ):
            max_range = 19
        else:
            max_range = len(splitSource)

        print ''
        print ''
        print ''
        ##print 'Keyword: ' + keyWord[i]
        print ''            

        for x in range (0, max_range):
            aTweet = re.sub(r'<.*?>','',splitSource[x])
            print (aTweet + '~' + timeSource[x] + '~' + keyWord[i])
            #print ';'
            newTwit.append(aTweet)

##        comparison = difflib.SequenceMatcher(None, newTwit, oldTwit)
##        howSim = comparison.ratio()
##        print ';'
##        print 'This selection is',howSim,'similar to the past'
##        howSimAr.append(howSim)
##        howSimAr.remove(howSimAr[0])
##
##        waitMultiplier = reduce(lambda x, y: x+y, howSimAr)/len(howSimAr)
##
##        print ''
##        print 'The current similarity array:',howSimAr
##        print 'Our current Multiplier:', waitMultiplier

        oldTwit = [None]
        for eachItem in newTwit:
            oldTwit.append(eachItem)

        newTwit = [None]

        time.sleep(2)
        x = 0
        i = i + 1

##    except Exception, e:
##        print str(e)
##        print 'errored in the main try'
main()

Answer 1

twitter搜索页面的源代码中没有出现js-nav" title="，因此第二个regexp将找不到任何内容。事实上

print "len(timeSource) =", len(timeSource)
print "max_range =", max_range

在

for x in range (0, max_range):

将显示：

len(timeSource) = 0
max_range = 20

无论您想归档什么，最好使用HTMLParser左右的文档来处理HTML，而不是使用re。这将更容易确保timeSource[x]和splitSource[x]在所有x中都属于彼此。你知道吗