Question

我正在处理一系列脚本，这些脚本从数据库中提取URL并使用textstat package根据一组预定义的计算来计算页面的可读性。下面的函数采用url（来自CouchDB），计算定义的可读性分数，然后将分数保存回相同的CouchDB文档。

我遇到的问题是错误处理。例如，Flesch Reading Ease得分计算需要计算页面上句子的总数。如果返回为零，则抛出异常。有没有办法捕获此异常，在数据库中保存异常的注释，然后转到列表中的下一个URL？我可以在下面的功能（首选）中执行此操作，还是需要编辑包本身？

我知道以前曾经问过这个问题的变体。如果您知道可以回答我的问题，请指出我的方向。到目前为止，我的搜索一直没有结果。提前谢谢。

def get_readability_data(db, url, doc_id, rank, index):
    readability_data = {}
    readability_data['url'] = url
    readability_data['rank'] = rank
    user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)'
    headers = { 'User-Agent' : user_agent }
    try:
        req = urllib.request.Request(url)
        response = urllib.request.urlopen(req)
        content = response.read()
        readable_article = Document(content).summary()
        soup = BeautifulSoup(readable_article, "lxml")
        text = soup.body.get_text()
        try:
            readability_data['flesch_reading_ease'] = textstat.flesch_reading_ease(text)
            readability_data['smog_index'] = textstat.smog_index(text)
            readability_data['flesch_kincaid_grade'] = textstat.flesch_kincaid_grade(text)
            readability_data['coleman_liau'] = textstat.coleman_liau_index(text)
            readability_data['automated_readability_index'] = textstat.automated_readability_index(text)
            readability_data['dale_chall_score'] = textstat.dale_chall_readability_score(text)
            readability_data['linear_write_formula'] = textstat.linsear_write_formula(text)
            readability_data['gunning_fog'] = textstat.gunning_fog(text)
            readability_data['total_words'] = textstat.lexicon_count(text)
            readability_data['difficult_words'] = textstat.difficult_words(text)
            readability_data['syllables'] = textstat.syllable_count(text)
            readability_data['sentences'] = textstat.sentence_count(text)
            readability_data['readability_consensus'] = textstat.text_standard(text)
            readability_data['readability_scores_date'] = time.strftime("%a %b %d %H:%M:%S %Y")

            # use the doc_id to make sure we're saving this in the appropriate place
            readability = json.dumps(readability_data, sort_keys=True, indent=4 * ' ')
            doc = db.get(doc_id)
            data = json.loads(readability)
            doc['search_details']['search_details'][index]['readability'] = data
            #print(doc['search_details']['search_details'][index])
            db.save(doc)
            time.sleep(.5)

        except: # catch *all* exceptions
            e = sys.exc_info()[0]
            write_to_page( "<p>---ERROR---: %s</p>" % e )

    except urllib.error.HTTPError as err:
        print(err.code)

这是我收到的错误：

Error(ASL): Sentence Count is Zero, Cannot Divide
Error(ASyPW): Number of words are zero, cannot divide
Traceback (most recent call last):
  File "new_get_readability.py", line 114, in get_readability_data
    readability_data['flesch_reading_ease'] = textstat.flesch_reading_ease(text)
  File "/Users/jrs/anaconda/lib/python3.5/site-packages/textstat/textstat.py", line 118, in flesch_reading_ease
    FRE = 206.835 - float(1.015 * ASL) - float(84.6 * ASW)
TypeError: unsupported operand type(s) for *: 'float' and 'NoneType'

这是调用函数的代码：

if __name__ == '__main__':
    db = connect_to_db(parse_args())
    print("~~~~~~~~~~" + " GETTING IDs " + "~~~~~~~~~~")
    ids = get_ids(db)
    for i in ids:
        details = get_urls(db, i)
        for d in details:
            get_readability_data(db, d['url'], d['id'], d['rank'], d['index'])

Answer 1

通常，优先考虑尽可能减少try: except:块。我会将你的textstat函数包装在某种类型的装饰器中，以捕获你期望的异常，并返回函数输出和捕获的异常。

例如：

def catchExceptions(exception):  #decorator with args (sorta boilerplate)
    def decorator(func):
        def wrapper(*args, **kwargs):
            try:
                retval = func(*args, **kwargs)
            except exception as e:
                return None, e
            else:
                return retval, None
        return wrapper
    return decorator

@catchExceptions(ZeroDivisionError)
def testfunc(x):
    return 11/x

print testfunc(0)
print '-----'
print testfunc(3)

打印：

(None, ZeroDivisionError('integer division or modulo by zero',))
-----
(3, None)

在Python中继续异常

1 个答案: