技术 | Python的从零开始系列连载（三十八）

最近看到有一个百度图片下载的Python爬取，很感兴趣，并在原来的基础上将py文件转换为exe文件。具体操作如下：

#coding:utf-8
import requests
import os
import re
import json
import itertools
import urllib
import sys

str_table = {
    '_z2C$q': ':',
    '_z&e3B': '.',
    'AzdH3F': '/'
}

char_table = {
    'w': 'a',
    'k': 'b',
    'v': 'c',
    '1': 'd',
    'j': 'e',
    'u': 'f',
    '2': 'g',
    'i': 'h',
    't': 'i',
    '3': 'j',
    'h': 'k',
    's': 'l',
    '4': 'm',
    'g': 'n',
    '5': 'o',
    'r': 'p',
    'q': 'q',
    '6': 'r',
    'f': 's',
    'p': 't',
    '7': 'u',
    'e': 'v',
    'o': 'w',
    '8': '1',
    'd': '2',
    'n': '3',
    '9': '4',
    'c': '5',
    'm': '6',
    '0': '7',
    'b': '8',
    'l': '9',
    'a': '0'
}
char_table = {ord(key): ord(value) for key, value in char_table.items()}

def decode(url):
	for key,value in str_table.items():
		url = url.replace(key,value)
	return url.translate(char_table)

def buildUrls(word):
    word = urllib.parse.quote(word)
    url = r"http://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&fp=result&queryWord={word}&cl=2&lm=-1&ie=utf-8&oe=utf-8&st=-1&ic=0&word={word}&face=0&istype=2nc=1&pn={pn}&rn=60"
    urls = (url.format(word=word, pn=x) for x in itertools.count(start=0, step=60))
    return urls

re_url = re.compile(r'"objURL":"(.*?)"')
def resolveImgUrl(html):
	imgUrls = [decode(x) for x in re_url.findall(html)]
	return imgUrls

def downImg(imgUrl,dirpath,imgName):
	filename = os.path.join(dirpath,imgName)
	try:
		res = requests.get(imgUrl,timeout=15)
		if str(res.status_code)[0] == '4':
			print(str(res.status_code),":",imgUrl)
			return False
	except Exception as e:
		print('抛出异常:',imgUrl)
		print(e)
		return False
	with open(filename+'.jpg','wb') as f:
		f.write(res.content)
	return True
def mkDir(dirName):
    dirpath = os.path.join(sys.path[0], dirName)
    if not os.path.exists(dirpath):
        os.mkdir(dirpath)
    return dirpath

if __name__ == '__main__':
    print("欢迎使用百度图片下载脚本！\n目前仅支持单个关键词。")
    print("下载结果保存在脚本目录下的img文件夹中。")
    print("=" * 50)
    word = input("请输入你要下载的图片关键词：\n")

    dirpath = mkDir("img")

    urls = buildUrls(word)
    index = 0
    for url in urls:
        print("正在请求：", url)
        html = requests.get(url, timeout=10).content.decode('utf-8')
        imgUrls = resolveImgUrl(html)
        if len(imgUrls) == 0:  # 没有图片则结束
            break
        for url in imgUrls:
            if downImg(url, dirpath, str(index) + ".jpg"):
                index += 1
                print("已下载 %s 张" % index)

pip install pyinstaller

pyinstaller -F baiduimg.py