urllib.robotparser — 互联网爬虫控制

测试访问权限

# urllib_robotparser_simple.py
from urllib import parse
from urllib import robotparser

AGENT_NAME = 'PyMOTW'
URL_BASE = 'https://pymotw.com/'
parser = robotparser.RobotFileParser()
parser.set_url(parse.urljoin(URL_BASE, 'robots.txt'))
parser.read()

PATHS = [
    '/',
    '/PyMOTW/',
    '/admin/',
    '/downloads/PyMOTW-1.92.tar.gz',
]

for path in PATHS:
    print('{!r:>6} : {}'.format(
        parser.can_fetch(AGENT_NAME, path), path))
    url = parse.urljoin(URL_BASE, path)
    print('{!r:>6} : {}'.format(
        parser.can_fetch(AGENT_NAME, url), url))
    print()

Long-lived Spiders

# urllib_robotparser_longlived.py
from urllib import robotparser
import time

AGENT_NAME = 'PyMOTW'
parser = robotparser.RobotFileParser()
# Using the local copy
parser.set_url('file:robots.txt')
parser.read()
parser.modified()

PATHS = [
    '/',
    '/PyMOTW/',
    '/admin/',
    '/downloads/PyMOTW-1.92.tar.gz',
]

for path in PATHS:
    age = int(time.time() - parser.mtime())
    print('age:', age, end=' ')
    if age > 1:
        print('rereading robots.txt')
        parser.read()
        parser.modified()
    else:
        print()
    print('{!r:>6} : {}'.format(
        parser.can_fetch(AGENT_NAME, path), path))
    # Simulate a delay in processing
    time.sleep(1)
    print()