Python语法笔记

url中含有中文的处理

Python编程：URL网址链接中的中文编码与解码
Python进行URL解码

from urllib.request import quote
...
	def start_requests(self):keywords = ['手机', '笔记本电脑', '键鼠套装']
        for keyword in keywords:
            url = r'https://s.taobao.com/search?q={}'.format(keyword)
            ret1 = quote(url, safe=";/?:@&=+$,", encoding="utf-8")
            yield scrapy.Request(url=ret1)

# -*- coding: utf-8 -*-

# @File    : urldecode_demo.py
# @Date    : 2018-05-11

from urllib.request import quote, unquote

# 编码
url1 = "https://www.baidu.com/s?wd=中国"

# utf8编码，指定安全字符
ret1 = quote(url1, safe=";/?:@&=+$,", encoding="utf-8")
print(ret1)
# https://www.baidu.com/s?wd=%E4%B8%AD%E5%9B%BD

# gbk编码
ret2 = quote(url1, encoding="gbk")
print(ret2)
# https%3A//www.baidu.com/s%3Fwd%3D%D6%D0%B9%FA

# 解码
url3 = "https://www.baidu.com/s?wd=%E4%B8%AD%E5%9B%BD"

ret3 = unquote(url3, encoding='utf-8')
print(ret3)
# https://www.baidu.com/s?wd=中国

python字符串前加r、f、u、l 的区别
python中 r'', b'', u'', f'' 的含义
含有中文的url前加u 亦可！

    def start_requests(self):keywords = ['手机', '笔记本电脑', '键鼠套装']
        for keyword in keywords:
            url = u'https://s.taobao.com/search?q={}'.format(keyword)
            yield scrapy.Request(url=url)