How To Search And Replace Text From One File To Another Using Python?

I have a file file1.txt : I Show more flower you can see by link All is Beautyfull.You Can View Here ! Link View : http://lincoln.com/view/12432134/flower1.jpg http://lincoln.

Solution 1:

Try this

import urlparse
import os

def file_merge(file1name,file2name):

    file1contents = list()
    file2contents = list()

    file1 = open(file1name, 'U')
    file1contents = file1.readlines()
    file1.close()

    file2 = open(file2name, 'U')
    file2contents = file2.readlines()
    file2.close()

    file3contents = []

    for link in file2contents:
        temp = urlparse.urlsplit(link)
        dirname, filename = os.path.split(temp.path)

        file3contents.append(link)

        linkin1 = False
        for l_link in file1contents[4:]:
            if l_link.endswith(filename):
                linkin1 = True

        if not linkin1:
            urllist = list(temp)
            urllist[1] = 'kashi.com'
            file3contents[-1] = urlparse.urlunsplit(urllist)


    file3 = open(file1name,'w')
    for line in file3contents:
        file3.write(line)
    file3.close()

file_merge('/tmp/file1.txt','/tmp/file2.txt')

Solution 2:

try this, please:

with open('file2.txt','r') as f2:
    dic2 = {}
    li2 = []
    for line in f2:
        spli = line.rstrip().replace('http://','').split('/')
        dic2[(spli[0],spli[-1])] = line if line[-1]=='\n' else line+'\n'
        li2.append((spli[0],spli[-1]))

with open('file1.txt','r') as f1,open('file3.txt','w') as f3:

    itr1 = iter(f1)

    for line in itr1:
        f3.write(line)
        if line.strip()=='':
            break

    for line in itr1:
        if line.strip():
            spli = line.rstrip().replace('http://','').split('/')
            x = (spli[0],spli[-1])
            if x in li2:
                f3.write(dic2[x])
                li2.remove((spli[0],spli[-1]))
    klu = '\n' if line.rstrip()==line else ''
    # to add a blank line if the last line wasn't '\n'-ended
    f3.write(klu + '\nMore Link VIew:\n\n')

    for remain in li2:
        f3.write(dic2[remain])

    f3.write('++++++++++++++++++++++++++++++++++++++++ ')

Solution 3:

This works; however it really seems to me very strange question in the first place...sorry...

from urlparse import urlparse
import os.path

def read_links2(f):
    for line in f:
        line = line.strip()
        url = urlparse(line)
        if url.scheme in ('http', 'https'):
            key = (url.netloc, os.path.split(url.path)[1])
            yield (key, url)

links2 = dict(read_links2(open('f2.txt', 'U')))

for line in open('f1.txt', 'U'):
    line = line.rstrip()
    url = urlparse(line)
    if url.scheme in ('http', 'https'):
        key = (url.netloc, os.path.split(url.path)[1])
        if key in links2:
            print links2[key].geturl()
    else:
        print line

print 'More Link VIew:'

for url in links2.values():
    if url.netloc == 'kashi.com':
        print url.geturl()


print '+++++++++++++++++++'