按照特定字符（此处选为字符’j’）分割文档成多个小文档
def main():with open("dir/origin.txt","r") as f:temp = f.readlines()words = []L = len(temp)for i in range(L):if "j" in temp[i] :words = temp[i]with open('dir/'+words[0:6]+'.txt', 'w') as g:for j in range(i+1, L):if "j" in temp[j]:breakg.write(temp[j])if __name__ == '__main__':main()
爬取网页静态图片
###coding=utf-8#####urllib模块提供了读取Web页面数据的接口##import urllib.request###re模块主要包含了正则表达式##import re###定义一个getHtml()函数##def getHtml(url):## page = urllib.request.urlopen(url) #urllib.urlopen()方法用于打开一个URL地址## html = page.read() #read()方法用于读取URL上的数据## return html####def getImg(html):## reg = r'src="(.+?\.jpg)" pic_ext' #正则表达式，得到图片地址## imgre = pile(reg)#pile() 可以把正则表达式编译成一个正则表达式对象.## imglist = re.findall(imgre,html)#re.findall() 方法读取html 中包含 imgre（正则表达式）的 数据## #把筛选的图片地址通过for循环遍历并保存到本地## #核心是urllib.urlretrieve()方法,直接将远程数据下载到本地，图片通过x依次递增命名## x = 0#### for imgurl in imglist:## urllib.request.urlretrieve(imgurl,'/Users/c-ten/Desktop/worm/%s.jpg' % x)## x+=1######html = getHtml("/search/index?tn=baiduimage&ct=26592&lm=-1&cl=2&ie=gbk&word=masked%20faces&hs=2&xthttps=000000&fr=ala&ori_query=masked%20faces&ala=0&alatpl=sp&pos=0")###print getImg(html)#<span style="color:#330099;">'''#Created on -4-17#@author: Administrator#'''import urllib.requestimport redef gethtml(url):html=urllib.request.urlopen(url)data=html.read()return data.decode("utf-8")def getimg(html):dir="/Users/c-ten/Desktop/worm/" #图片保存路径reg='src="(.+?\.jpg)" pic_ext' imgreg=pile(reg)imglist=imgreg.findall(html)x=0for i in imglist:print(i)urllib.request.urlretrieve(i,'{}{}.jpg'.format(dir, x))x=x+1print('gethtml')html=gethtml("/search/index?tn=baiduimage&ct=26592&lm=-1&cl=2&ie=gbk&word=%BF%DA%D5%D6%C3%B1%D7%D3%D5%DA%B5%B2%C8%CB%C1%B3%CD%BC%C6%AC&hs=2&xthttps=000000&fr=ala&ori_query=%E5%8F%A3%E7%BD%A9%E5%B8%BD%E5%AD%90%E9%81%AE%E6%8C%A1%E4%BA%BA%E8%84%B8%E5%9B%BE%E7%89%87&ala=0&alatpl=sp&pos=0")print('getimg')getimg(html)#</span><span style="color:#333333;">#</span>
计算文档行数
def main():with open("list.txt","r") as f:temp = f.readlines()L = len(temp)print(L)f.close()if __name__ == '__main__':main()
批量增加后缀名
# -*- coding: cp936 -*-import ospath = 'jpg_files_dir'for file in os.listdir(path):if os.path.isfile(os.path.join(path,file))==True:if file.find('.')<0:newname=file+'.jpg'os.rename(os.path.join(path,file),os.path.join(path,newname))
如果觉得《python批处理实现爬取网页静态图片文件重命名图片统一修改大小等功能》对你有帮助，请点赞、收藏，并留下你的观点哦！
