下载维基百科页面的全部历史记录

import mwclient
import json
import time

site = mwclient.Site('en.wikipedia.org')
page = site.pages['Wikipedia']

for i, (info, content) in enumerate(zip(page.revisions(), page.revisions(prop='content'))):
    info['timestamp'] = time.strftime("%Y-%m-%dT%H:%M:%S", info['timestamp'])
    print(i, info['timestamp'])
    open("%s.json" % info['timestamp'], "w").write(json.dumps(
        { 'info': info,
            'content': content}, indent=4))

漫无目的地四处游荡,寻找另一个问题的线索,我用我自己的方式说,我对这个话题一无所知!我是在读了你的问题后发现这个问题的: http://mwclient.readthedocs.io/en/latest/reference/page.html .看看 revisions

http://mwclient.readthedocs.io/en/latest/user/page-ops.html#listing-page-revisions .

使用 mwclient

#!/usr/bin/env python3
import logging, mwclient, pickle, os
from mwclient import Site
from mwclient.page import Page
logging.root.setLevel(logging.DEBUG)

logging.debug('getting page...')
env_page = os.getenv("MEDIAWIKI_PAGE")
page_name = env_page is not None and env_page or 'Stack Overflow'
page_name = Page.normalize_title(env_page)
site = Site('en.wikipedia.org') # https by default. change w/`scheme=`
page = site.pages[page_name]

logging.debug('extracting revisions (may take a really long time, depending on the page)...')
revisions = []
for i, revision in enumerate(page.revisions()):
    revisions.append(revision)

logging.debug('saving to file...')
with open('{}Revisions.mediawiki.pkl'.format(page_name), 'wb+') as f:
    pickle.dump(revisions, f, protocol=0) # protocol allows backwards compatibility between machines