如果嵌套在for循环中，python会损坏

Question

我正在尝试在下面的代码中运行带有计数器的循环。

import sys
import imaplib
import getpass
import email
import email.header
import datetime
from bs4 import BeautifulSoup 
import re
from lxml import etree, html
from HTMLParser import HTMLParser


EMAIL_ACCOUNT = "sample@gmail.com"
EMAIL_FOLDER = "INBOX"


def stringify_children(node):
    from lxml.etree import tostring
    from itertools import chain
    parts = ([node.text] +
            list(chain(*([c.text, tostring(c), c.tail] for c in node.getchildren()))) +
        [node.tail])
    # filter removes possible Nones in texts and tails
    return ''.join(filter(None, parts))

def process_mailbox(M):
    """
    Do something with emails messages in the folder.  
    For the sake of this example, print some headers.
    """

    rv, data = M.search(None, "ALL")
    if rv != 'OK':
        print "No messages found!"
        return
    for num in data[0].split(): 
        rv, data = M.fetch(num, '(RFC822)')
        if rv != 'OK':
            print "ERROR getting message", num
            return

        msg = email.message_from_string(data[0][1])

        if msg.is_multipart():
            html = None
            print "Checking for html or text"
            for part in msg.get_payload():
                if part.get_content_charset() is None:
                    charset = chardet.detect(srt(part))['encoding']
                else:
                    charset = part.get_content_charset()
                if part.get_content_type() == 'text/plain':
                    text = unicode(part.get_payload(decode=True),str(charset),"ignore").encode('utf8','replace')
                    f = open('email.txt', 'w')
                    f.write(text)
                    f.close
                if part.get_content_type() == 'text/html':
                    html = unicode(part.get_payload(decode=True),str(charset),"ignore").encode('utf8','replace')
                    f = open('email.html','w')
                    f.write(html)
                    f.close
                if part.get('Content-Disposition') is None:
                    continue

                filename = part.get_filename()

                if not os.path.isfile(filename) :
                    fp = open(filename, 'wb')
                    fp.write(part.get_payload(decode=True))
                    fp.close()
                    return 0

            if html is None:
                return text.strip()
            else:
                return html.strip()


class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.fed = []
    def handle_data(self, d):
        self.fed.append(d)
    def get_data(self):
        return ''.join(self.fed)

def strip_tags(html):
    s = MLStripper()
    s.feed(html)
    return s.get_data()





def parse_html():
    htmldoc = open('email.html', 'r+')
    doc = htmldoc.read()
    doc = re.sub('foobar', 'bar', doc)
    soup = BeautifulSoup(open("email.html"))
    VALID_TAGS = ['iframe', 'video', 'o>', 'li', 'sub', 'sup', 'source', 'br', 'h3', 'h4', 'h6', 'hr', 'q', 'mark','wbr', 'audio','strong', 'em', 'p','ul', 'li', 'br', 'blockquote', 'pre', 'del', 'h3', 'body', 'header', 'html', 'title', 'div', 'img', 'a']

    for tag in soup.findAll(True):
        if tag.name == 'i':
            tag.name = 'em'
        elif tag.name == 'cite':
            tag.name = 'em'
        elif tag.name == 'b':
            tag.name = 'strong'
        elif tag.name == 'kdb':
            tag.name = 'strong'
        elif tag.name == 'var':
            tag.name = 'strong'
        elif tag.name == 'aside':
            tag.name = 'blackquote'
        elif tag.name == 'code':
            tag.name = 'pre'
        elif tag.name == 'samp':
            tag.name = 'pre'
        elif tag.name == 's':
            tag.name = 'del'
        elif tag.name == 'h1':
            tag.name = 'h3'
        elif tag.name == 'h2':
            tag.name = 'h3'

    pretty_soup = soup.prettify()
    docstring = str(pretty_soup)
    tree = etree.fromstring(docstring)
    walkAll = tree.iterchildren() 

    count = 0
    for elt in walkAll:
        if count <= 300: 
            child = stringify_children(elt)
            childtext = strip_tags(child)
            childstring = childtext.replace(" ", "")
            for i in childstring:
                count = count + len(i)
                print count

        else:
            root = etree.Element("elt")
            root.text = ''
            root.tail = ''

    etroot = tree.getroottree()
    results = etree.tostring(etroot)
    htmldoc.write(results)





M = imaplib.IMAP4_SSL('imap.gmail.com')

try:
    rv, data = M.login(EMAIL_ACCOUNT, getpass.getpass())
except imaplib.IMAP4.error:
    print "LOGIN FAILED!!! "
    sys.exit(1)

print rv, data

rv, mailboxes = M.list()
if rv == 'OK':
    print "Mailboxes:"
    print mailboxes

rv, data = M.select(EMAIL_FOLDER)
if rv == 'OK':
    print "Processing mailbox...\n"
    process_mailbox(M)
    M.close()
    parse_html()
else:
    print "ERROR: Unable to open mailbox ", rv

M.logout()

但是我下面的循环坏了，我不明白为什么。当计数达到 300 时，应该执行 else 语句中的代码，但计数器会继续遍历元素。

我希望在计数达到 300 之后对每个元素执行 else 语句。结果会影响达到 300 之后的元素，并且在计数达到 300 之前迭代的元素不会受到影响。我在 else 语句中放了一个打印“测试”来测试它，它没有被打印出来。

此代码的目的是抓取一封电子邮件并计算电子邮件中的文本，当总文本计数达到某个参数时，在本例中为 300，否则执行并清除剩余元素中的文本。我随机用了300。文本限制也可以是 50。

count = 0
for elt in walkAll:
    if count <= 300: 
       child = stringify_children(elt)
       childtext = strip_tags(child)
       childstring = childtext.replace(" ", "")
           for i in childstring:
               count = count + len(i)
               print count

    else:
        root = etree.Element("elt")
        root.text = ''
        root.tail = ''

编辑

我可以在 count = count + len(i) 之后插入一个 if break 条件，这将停止循环，如下所示：

count = 0
for elt in walkAll:
    if count <= 300: 
        child = stringify_children(elt)
        childtext = strip_tags(child)
        childstring = childtext.replace(" ", "")
        for i in childstring:
            count = count + len(i)
            if count >= 300:
                break
            print count

    else:
        root = etree.Element("elt")
        root.text = ''
        root.tail = ''

这打破了计数，但 else 语句仍然没有运行

Answer 1

不确定我是否完全理解您想要做的事情，但根据您上面的代码，这应该可以工作。

for elt in walkAll:
    count = 0
    child = stringify_children(elt)
    childtext = strip_tags(child)
    childstring = childtext.replace(" ", "")
    for s in childstring:
        count+=1
        if count >= 300:
            root = etree.Element("elt")
            root.text = ''
            root.tail = ''