python操作随笔

# -*- encoding: utf-8 -*-
import urllib2
from bs4 import BeautifulSoup
import re

f1 = open('E:/1.txt')
line = f1.readline()  # 调用文件的 readline()方法
list1 = []
while line:
    list1.append(line)
    line = f1.readline()
    #print line

f = open('E:/txt1.txt', 'a')
for ele in list1:
    url = 'https://cn.bing.com/dict/search?q='+ele+''
    response = urllib2.urlopen(url)
    dd = response.read()
    s = re.search('更多例句筛选(.*)sb_pagS', dd)
    mm = s.group()
    soup = BeautifulSoup(mm, "html.parser")
    listurl = soup.find_all(['span', 'a'])
    str = ''
    get = ''

    times = 0
    ifprit = 0
    for url in listurl:
        times += 1
        if url.attrs.has_key(u'class') == True:
            if url.attrs[u'class'] == [u'p1-3']:
                continue

        get = url.get_text()
        if get.strip() == '':
            continue
        d = get[0]
        if ord(d) < 300:
            str += get + " "
            ifprit = 1
        else:
            if ifprit == 1:
                ifprit = 0
                try:
                    f.write(str)
                except:
                    continue
            str = '\n '
            get = ''
    print ele
f.close()

转载于:https://www.cnblogs.com/ytCui/p/9150886.html