将分隔字符串从输入文件写入输出文件

Question

目的是搜索一个 infile (html) 并在一个可以传递给 wget 的 outfile 中重现任何图像的 URL。这将是我用 Python 编写的第一个有用的东西，它似乎在 Fedora 上运行良好。我在任何地方都找不到像这样的东西。有人对此有改进建议吗？

import fileinput
import re
#replace 'output.txt' with the name of your outfile
file = open('output.txt', 'w')

#prefix and postfix are how we discriminate your substring from the infile's line
prefix = '<img src='
postfix = '.jpg'

#read through the infile line-by-line
for line in fileinput.input():
    if re.search(prefix, line):
        #from if above, if you find the prefix, assign the integer to first_index
        first_index = line.index(prefix)
            if re.search(postfix, line):
                #same as comment above, but for postfix
                second_index = line.index(postfix)
                #write your string plus an newline to the outfile
                file.write(line[first_index+prefix.__len__():second_index+postfix.__len__()]+'\n')

Answer 1

我过去做过类似的事情，效果很好......我相信它会比尝试使用正则表达式解析更准确。

from HTMLParser import HTMLParser


class ImageFinder(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.file = open('output.txt', 'w') 
    def handle_starttag(self, tag, attrs):
        if tag == "img":
            url = [u[1] for u in attrs if u[0] == "src"][0]
            self.file.write(url+"\n")
    def __exit__(self):
        self.file.close()

inputdata = open("myfile.txt").read()
parser = ImageFinder()
parser.feed(inputdata)