航空摄影图库图片爬虫脚本

# -*- 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.修改爬取的页数(1,10),默认爬取9页
    for pages in range(1, 10):
        page = str(pages)
        # http://www.aerophotos.cn/index.php?mod=search&code=search_plane&page_count=15&page=2
        url = "http://www.aerophotos.cn/index.php?mod=search&code=search_plane&page_count=15&page=" + page
        print(url)
        try:
            txt = requests.get(url, headers=headers).text
            doc = PyQuery(txt)
            # print(doc)
            air_names = doc(".nr1 td:nth-child(3)").items()
            air_nam