htmlnames = []
imagelist = []
tempstring = ''
filenames = os.listdir('/home/gregp/development/Scribus15x/doc/en/')
for name in filenames:
if name.endswith('.html'):
htmlnames.append(name)
#print htmlnames
for htmlfile in htmlnames:
all_text = open('/home/gregp/development/Scribus15x/doc/en/' + htmlfile).read()
linelength = len(all_text)
index = 3
while index < linelength:
if (all_text[index] == '='):
if (all_text[index-3] == 's') and (all_text[index-2] == 'r') and
(all_text[index-1] == 'c'):
imagefound(all_text, imagelist, index)
推荐阅读
沙龙晃荡 | 3月31日 京东、微博、华为拭魅战专家与你合营商量容器技巧实践! 2015年,固执的苹不雅也推出了带压力感应的手写笔,然则迄今为止,这个笔如今只能在iPad Pro上应用,这让苹不雅>>>详细阅读
本文标题:如何用Python解析HTML?
地址:http://www.17bianji.com/lsqh/40963.html
1/2 1