# -*- 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()
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")
print(res)
# -------------
90设计网爬虫
最新推荐文章于 2021-06-08 21:14:53 发布