python实现将固定格式的字符串调整为字典的格式，用于爬虫爬取数据时快速添加请求数据

Posted 2020-12-07 坚持是一种习惯

#!/usr/local/bin/python3.7

"""
@File    :   str_replace.py
@Time    :   2020/06/03
@Author  :   Mozili

"""# 输入多行字符串
data = []
str = input(‘输入要调整的字符串：
‘)
data.append(str)
stopword = ‘‘#停止条件

for line in iter(input,stopword):#iter()中第一个参数是可调用的，即可以像函数一样调用他，因此是input，而不是input（）
    data.append(line.split())

# print(data)
# 遍历列表
for i in range(len(data)):
    if ‘:‘ in data[0]:
        if i==0:
            s0 = data[0].split(‘:‘)[0]
            s1 = data[0].split(‘:‘)[1].strip(‘ ‘)
            # 给字符串加单引号
            s0 = ‘{}{}{}‘.format("‘", s0, "‘")
            s1 = ‘{}{}{}‘.format("‘", s1, "‘")
            # 拼接成一个新的字符串
            new_str = ‘data = ‘ + ‘{‘ + ‘
 ‘ + s0 + ‘:‘ + s1 + ‘,‘  
        else:
            s0 = data[i][0].split(":")[0]
            s1 = data[i][1]
            s0 = ‘{}{}{}‘.format("‘", s0, "‘")
            s1 = ‘{}{}{}‘.format("‘", s1, "‘")
            if i==len(data)-1:
                new_str = ‘ ‘ + s0 + ‘:‘ + s1 + ‘
‘ + ‘}‘
            else:
                new_str = ‘ ‘ + s0 + ‘:‘ + s1 + ‘,‘
    elif ‘&‘ in data[0]:
        # 以&分割字符串
        s_list = data[0].split(‘&‘)
        # print(s_list)
        for n in range(len(s_list)):
            # 将字符串中的=换成:
            str = s_list[n].replace(‘=‘, ‘:‘)
            # print(str)
            # 把字符串转为list
            str_list = list(str)
            # print(str_list)
            # 确认:在列表中的索引值
            i = str_list.index(‘:‘)
            # print(i)
            # 在:的前面添加‘
            str_list.insert(i, "‘")
            # 在:的后面添加‘
            str_list.insert(i+2, "‘")
            # 将list转换为str
            str = ‘‘.join(str_list)
            # 给字符串添加单引号
            str = ‘{}{}{}‘.format("‘", str, "‘")
            if n==0:
                new_str = ‘data = ‘ + ‘{‘ + ‘
 ‘ + str + ‘,‘
            else:
                if n==len(s_list)-1:
                    new_str = ‘ ‘ + str + ‘}‘
                else:
                    new_str = ‘ ‘ + str + ‘,‘
            print(new_str)

            
    else:
        i=0
        while i < len(data):
            # print(i)
            if i==0:
                s = data[0].split(‘ ‘)
                # 获取第一个字符串
                s0 = s[0]
                # 给字符串加单引号
                s0 = ‘{}{}{}‘.format("‘", s0, "‘")
                # 获取第二个字符串
                s1 = s[1]
                s1 = ‘{}{}{}‘.format("‘", s1, "‘")
                new_str = ‘data = ‘ + ‘{‘ + ‘
 ‘ + s0 + ‘:‘ + s1 + ‘,‘ 
            else:
                # 判断列表的长度，处理没有值的键值对
                if len(data[i])==1:
                    s = data[i][0]
                    s0 = ‘{}{}{}‘.format("‘", s, "‘")
                    new_str = ‘ ‘ + s0 + ‘:‘ + "‘‘" + ‘,‘
                else:
                    s0 = data[i][0]
                    s1 = data[i][1]
                    # 给字符串添加单引号
                    s0 = ‘{}{}{}‘.format("‘", s0, "‘")
                    s1 = ‘{}{}{}‘.format("‘", s1, "‘")
                    # 判断是否是最后一组数据
                    if i == len(data)-1:
                        new_str = ‘ ‘ + s0 + ‘:‘ + s1 + ‘}‘
                    else:
                        new_str = ‘ ‘ + s0 + ‘:‘ + s1 + ‘,‘
            i+=1
            print(new_str)
        break
           
    print(new_str)
   
    
# 支持替换以下三种格式的字符串
str1 = """
email 18827441xxxx
icode 
origURL http://www.renren.com/home
domain renren.com
key_id 1
captcha_type web_login
password 32904758c29a901f87064f3aa151f9c373112ed66370fe9b28152f0ce63d3796
rkey d6b3acc434f19c92fad1f33176e506f0
f https%3A%2F%2Fbaidu.com%2F
"""
str2 = """
from: en
to: zh-Hans
text: cat
"""
str3 = "ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=baidu&wd=python中正则替换"