python执行程序最后一行,Python：只写最后一行输出

Trying to write a program that extracts URLs from a website. The output is good, but when I try to write the output to a file, only the last record is written. Here is the code:

import re

import urllib.request

# Retrieves URLs from the HTML source code of a website

def extractUrls(url, unique=True, sort=True, restrictToTld=None):

# Prepend "www." if not present

if url[0:4] != "www.":

url = "".join(["www.",url])

# Open a connection

with urllib.request.urlopen("http://" + url) as h:

# Grab the headers

headers = h.info()

# Default charset

charset = "ISO-8859-1"

# If a charset is in the headers then override the default

for i in headers:

match = re.search(r"charset=([\w\-]+)", headers[i], re.I)

if match != None:

charset = match.group(1).lower()

break

# Grab and decode the source code

source = h.read().decode(charset)

# Find all URLs in the source code

matches = re.findall(r"http\:\/\/(www.)?([a-z0-9\-\.]+\.[a-z]{2,6})\b", source, re.I)

# Abort if no URLs were found

if matches == None:

return None

# Collect URLs

collection = []

# Go over URLs one by one

for url in matches:

url = url[1].lower()

# If there are more than one dot then the URL contains

# subdomain(s), which we remove

if url.count(".") > 1:

temp = url.split(".")

tld = temp.pop()

url = "".join([temp.pop(),".",tld])

# Restrict to TLD if one is set

if restrictToTld:

tld = url.split(".").pop()

if tld != restrictToTld:

continue

# If only unique URLs should be returned

if unique:

if url not in collection:

collection.append(url)

# Otherwise just add the URL to the collection

else:

collection.append(url)

# Done

return sorted(collection) if sort else collection

# Test

url = "msn.com"

print("Parent:", url)

for x in extractUrls(url):

print("-", x)

f = open("f2.txt", "w+", 1)

f.write( x )

f.close()

The output is:

Parent: msn.com

- 2o7.net

- atdmt.com

- bing.com

- careerbuilder.com

- delish.com

- discoverbing.com

- discovermsn.com

- facebook.com

- foxsports.com

- foxsportsarizona.com

- foxsportssouthwest.com

- icra.org

- live.com

- microsoft.com

- msads.net

- msn.com

- msnrewards.com

- myhomemsn.com

- nbcnews.com

- northjersey.com

- outlook.com

- revsci.net

- rsac.org

- s-msn.com

- scorecardresearch.com

- skype.com

- twitter.com

- w3.org

- yardbarker.com

[Finished in 0.8s]

Only "yardbarker.com" is written to the file. I appreciate the help, thank you.

解决方案

url = "msn.com"

print("Parent:", url)

f = open("f2.txt", "w",)

for x in extractUrls(url):

print("-", x)

f.write( x )

f.close()