站酷海洛网图片爬虫

# -*- coding:utf-8 -*-import osimport requestsimport urllibfrom pyquery import PyQueryimport uuidfrom pypinyin import pinyinimport unicodedataheaders = { "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")