贴代码(初版,没有排版,更改,封装):
1.爬虫部分
一开始找到百度壁纸,个人比较喜欢雪景,所以想用爬虫批量下载,结果发现百度壁纸是动态的,就用request结果还是不行,所以最后又不得不用phantomjs来获取网页远吗,后来获取源码以后,解析出来了图片的url地址,然而mdzz用urlretrieve下载,结果百度给403foribidden了,后来一直在找办法,什么访问带头部,GG,什么发放稳获取response然后写入文件,GG,最后想到了unbuntu系统里面的wget来下载,于是写入文件,然后wget-i文件名进行批量下载,可以下,但是wget访问频率太快,在下载十多张图片之后就会被百度封了,于是查看wget命令,发现-w(-wait)课进行休眠,于是准备合理化访问。
2.图片背景自动更换设置(win10)
个性化-背景-背景-幻灯片放映,选择图片存储的文件夹,done
import urllib
'''
from urllib import request
from bs4 import BeautifulSoup as bs
url = "http://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%D1%A9%BE%B0%D7%C0%C3%E6%B1%DA%D6%BD&fr=ala&ala=1&pos=0&alatpl=wallpaper&oriquery=%E9%9B%AA%E6%99%AF%E6%A1%8C%E9%9D%A2%E5%A3%81%E7%BA%B8"
response = request.urlopen(url).read()
content = str(response,encoding = "utf-8")
bs_obj = bs(content,"html.parser")
print(bs_obj)
'''
#urlopen是最简单的但tmd也是最垃圾的over
#下面有请我们最高级的phatomjs
from selenium import webdriver
driver = webdriver.PhantomJS()
driver.set_window_size(25600,14400)
driver.get("http://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gbk&word=%D1%A9%BE%B0%B1%DA%D6%BD&fr=ala&ala=1&pos=0&alatpl=wallpaper&oriquery=%E9%9B%AA%E6%99%AF%E5%A3%81%E7%BA%B8s")
page_source = driver.page_source
#print(page_source)
#print(page_source)
#有请伟大的re
#伟大的re失败了。。。这尼玛代码还会自动消失出现,!绝了
'''
import re
pattern = re.compile(r'src="http://.*?.jpg"')
img_src_list = pattern.findall(page_source,re.I)
url_pattern = re.compile(r'http://.*?.jpg')
img_url_list = []
for i in img_src_list:
img_url_list.append(url_pattern.find(i,re.I))
for i in img_url_list:
print(i)
'''
#有请老伙伴bs4
#init download path
download_path = r"C:\Users\Mr.Guo\Pictures\BDpictures"
from bs4 import BeautifulSoup
import requests
from urllib import request
bs_obj = BeautifulSoup(page_source,"html.parser")
img_url_list = bs_obj.findAll("img",{"class":"main_img img-hover"})
final_url_list = []
for i in img_url_list:
final_url_list.append(i.attrs["src"])
#print(final_url_list)
f = open(download_path+"\test.txt",'a')
for i in range(len(final_url_list)):
print(final_url_list[i])
try:
'''
opener=request.build_opener()
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36')]
request.install_opener(opener)
#request.urlretrieve(url=url,filename=‘%s/%s.txt‘%(savedir,get_domain_url(url=url)))
request.urlretrieve(final_url_list[i],download_path+"\%s.jpg"%i)
'''
'''
r = requests.get(final_url_list[i])
i_download_path = download_path + "\%s.jpg"%i
with open(i_download_path, "wb") as code:
code.write(r.content)
'''
f.write(final_url_list[i]+'\n')
except Exception as e:
print(e)
pass