Strip HTML from strings in Python

Question

from mechanize import Browser
br = Browser()
br.open(\'http://somewebpage\')
html = br.response().readlines()
for line in html:
  print line

When p

Answer 1

This is a quick fix and can be even more optimized but it will work fine. This code will replace all non empty tags with "" and strips all html tags form a given input text .You can run it using ./file.py input output

    #!/usr/bin/python
import sys

def replace(strng,replaceText):
    rpl = 0
    while rpl > -1:
        rpl = strng.find(replaceText)
        if rpl != -1:
            strng = strng[0:rpl] + strng[rpl + len(replaceText):]
    return strng


lessThanPos = -1
count = 0
listOf = []

try:
    #write File
    writeto = open(sys.argv[2],'w')

    #read file and store it in list
    f = open(sys.argv[1],'r')
    for readLine in f.readlines():
        listOf.append(readLine)         
    f.close()

    #remove all tags  
    for line in listOf:
        count = 0;  
        lessThanPos = -1  
        lineTemp =  line

            for char in lineTemp:

            if char == "<":
                lessThanPos = count
            if char == ">":
                if lessThanPos > -1:
                    if line[lessThanPos:count + 1] != '<>':
                        lineTemp = replace(lineTemp,line[lessThanPos:count + 1])
                        lessThanPos = -1
            count = count + 1
        lineTemp = lineTemp.replace("<","<")
        lineTemp = lineTemp.replace(">",">")                  
        writeto.write(lineTemp)  
    writeto.close() 
    print "Write To --- >" , sys.argv[2]
except:
    print "Help: invalid arguments or exception"
    print "Usage : ",sys.argv[0]," inputfile outputfile"