# -*- coding:utf-8 -*- import os import requests import urllib from pyquery import PyQuery import uuid from pypinyin import pinyin import unicodedata headers = { "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome" "/75.0.3770.142 Safari/537.36" } def href_url_download(): # 1.填写要爬取关键词的list.txt keyword_list = open("list.txt", 'r', encoding='utf-8') lines = keyword_list.readlines() keyword_list.close() for keyword in lines: keyword = keyword.strip() print(keyword) # ------------------------汉字转化成拼音------------------------------------- # word = pinyin(keyword) # pin_yin = "".join(str(i[0]) for i in word) # print(pin_yin) # res = unicodedata.normalize('NFKD', pin_yin).encode('ascii', 'ignore').decode("ascii") 讯享网
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容，请联系我们，一经查实，本站将立刻删除。
如需转载请保留出处：https://51itzy.com/kjqy/31809.html