fileinput — 命令行过滤框架

Converting M3U files to RSS

for line in fileinput.input(sys.argv[1:]):
    mp3filename = line.strip()
    if not mp3filename or mp3filename.startswith('#'):
        continue
    item = SubElement(rss, 'item')
    title = SubElement(item, 'title')
    title.text = mp3filename
    encl = SubElement(item, 'enclosure',
                      {'type': 'audio/mpeg',
                       'url': mp3filename})

# fileinput_example.py
import fileinput
import sys
import time
from xml.etree.ElementTree import Element, SubElement, tostring
from xml.dom import minidom

# Establish the RSS and channel nodes
rss = Element('rss',
              {'xmlns:dc': "http://purl.org/dc/elements/1.1/",
               'version': '2.0'})
channel = SubElement(rss, 'channel')
title = SubElement(channel, 'title')
title.text = 'Sample podcast feed'
desc = SubElement(channel, 'description')
desc.text = 'Generated for PyMOTW'
pubdate = SubElement(channel, 'pubDate')
pubdate.text = time.asctime()
gen = SubElement(channel, 'generator')
gen.text = 'https://pymotw.com/'

for line in fileinput.input(sys.argv[1:]):
    mp3filename = line.strip()
    if not mp3filename or mp3filename.startswith('#'):
        continue
    item = SubElement(rss, 'item')
    title = SubElement(item, 'title')
    title.text = mp3filename
    encl = SubElement(item, 'enclosure',
                      {'type': 'audio/mpeg',
                       'url': mp3filename})

rough_string = tostring(rss)
reparsed = minidom.parseString(rough_string)
print(reparsed.toprettyxml(indent="  "))

Progress Metadata

# fileinput_grep.py
import fileinput
import re
import sys

pattern = re.compile(sys.argv[1])

for line in fileinput.input(sys.argv[2:]):
    if pattern.search(line):
        if fileinput.isstdin():
            fmt = '{lineno}:{line}'
        else:
            fmt = '{filename}:{lineno}:{line}'
        print(fmt.format(filename=fileinput.filename(),
                         lineno=fileinput.filelineno(),
                         line=line.rstrip()))

In-place Filtering

# etc_hosts.txt before modifications
##
# Host Database
#
# localhost is used to configure the loopback interface
# when the system is booting.  Do not change this entry.
##
127.0.0.1       localhost
255.255.255.255 broadcasthost
::1             localhost
fe80::1%lo0     localhost
10.16.177.128  hubert hubert.hellfly.net
10.16.177.132  cubert cubert.hellfly.net
10.16.177.136  zoidberg zoidberg.hellfly.net

# fileinput_change_subnet.py
import fileinput
import sys

from_base = sys.argv[1]
to_base = sys.argv[2]
files = sys.argv[3:]

for line in fileinput.input(files, inplace=True):
    line = line.rstrip().replace(from_base, to_base)
    print(line)

# etc_hosts.txt after modifications
##
# Host Database
#
# localhost is used to configure the loopback interface
# when the system is booting.  Do not change this entry.
##
127.0.0.1       localhost
255.255.255.255 broadcasthost
::1             localhost
fe80::1%lo0     localhost
10.17.177.128  hubert hubert.hellfly.net
10.17.177.132  cubert cubert.hellfly.net
10.17.177.136  zoidberg zoidberg.hellfly.net

# fileinput_change_subnet_noisy.py
import fileinput
import glob
import sys

from_base = sys.argv[1]
to_base = sys.argv[2]
files = sys.argv[3:]

for line in fileinput.input(files, inplace=True):
    if fileinput.isfirstline():
        sys.stderr.write('Started processing {}\n'.format(
            fileinput.filename()))
        sys.stderr.write('Directory contains: {}\n'.format(
            glob.glob('etc_hosts.txt*')))
    line = line.rstrip().replace(from_base, to_base)
    print(line)

sys.stderr.write('Finished processing\n')
sys.stderr.write('Directory contains: {}\n'.format(
    glob.glob('etc_hosts.txt*')))