Python 从解析的HTML中删除转义序列

我正在使用Python

mechanize

模块向网站提交一个简单的查询，然后分解返回的元素以获得所需的数据。但我似乎无法正确处理返回的转义序列。这是我的密码：

def stripEscape(string):    #credit goes to sarnold
    delete = ""
    i=1
    while (i<0x20):
        delete += chr(i)
        i += 1
    t = string.translate(None, delete)
    return t

def getHTML(metID):
    br = mechanize.Browser()
    response = br.open("http://urlgoeshere.com")

    br.form = list(br.forms())[0]
    br["PROMPT12"] = metID

    response = br.submit()
    htmlText = response.read()
    parseHTML(htmlText)

def parseHTML(htmlText):
    htmlText.index('table')
    arr = re.split(r'(</?\w{2}>)',htmlText)   # everything after background tag 
    logFile = open('Log.txt','wb')

    for ele in arr:
        ele = stripEscape(ele)
        if ele == '':
            arr.remove(ele)

    for ele in arr:
        logFile.write("ele: "+ele+'\n') 
        if re.match('/table', ele):
            logFile.write("END OF TABLE FOUND")
            logFile.write("\nele: "+ele+'\n')
            break
        # other element filters

def stripeescape（string）：#归功于sarnold
delete=“”
i=1
而（i第一个for循环中的ele元素未保存到数组中

for ele in arr:
    ele = stripEscape(ele)
    if ele == '':
        arr.remove(ele)

这部分代码只会更改
ele
元素NOT，
arr
arr
将保持不变。因此，所有转义序列都将NOT删除。您可以在该循环之后打印
arr
来测试它

因此，您需要做的是将其保存为新数组，然后供下一个循环使用

for ele in arr:
    if ele != "":
        newArray.append(stripEscape(ele))


for ele in newArray:
    logFile.write("ele: "+ele+'\n') 
    if re.match('/table', ele):
        logFile.write("END OF TABLE FOUND")
        logFile.write("\nele: "+ele+'\n')
        break

绝对是一个脸掌的时刻。应该看到的。
for ele in arr:
    if ele != "":
        newArray.append(stripEscape(ele))


for ele in newArray:
    logFile.write("ele: "+ele+'\n') 
    if re.match('/table', ele):
        logFile.write("END OF TABLE FOUND")
        logFile.write("\nele: "+ele+'\n')
        break