gpt4 book ai didi

python-2.7 - 如何从 Wikidata Id 获取 Wikipedia 页面?

转载 作者:行者123 更新时间:2023-12-04 11:03:04 25 4
gpt4 key购买 nike

如何从 Wikidata Id(例如:Q19675)获取 Wikipedia 页面(使用特定语言,比如法语)?这个问题似乎很明显,但奇怪的是,我在网上一无所获。我正在寻找可以与 requests Python 模块一起使用的 url 命令,例如:

url = "https://www.wikidata.org/w/api.php?action=some_method&ids=Q19675"
r = requests.post(url, headers={"User-Agent" : "Magic Browser"})

有人可以帮助我吗?

最佳答案

在 python 中,你可以这样做:

def get_wikipedia_url_from_wikidata_id(wikidata_id, lang='en', debug=False):
import requests
from requests import utils

url = (
'https://www.wikidata.org/w/api.php'
'?action=wbgetentities'
'&props=sitelinks/urls'
f'&ids={wikidata_id}'
'&format=json')
json_response = requests.get(url).json()
if debug: print(wikidata_id, url, json_response)

entities = json_response.get('entities')
if entities:
entity = entities.get(wikidata_id)
if entity:
sitelinks = entity.get('sitelinks')
if sitelinks:
if lang:
# filter only the specified language
sitelink = sitelinks.get(f'{lang}wiki')
if sitelink:
wiki_url = sitelink.get('url')
if wiki_url:
return requests.utils.unquote(wiki_url)
else:
# return all of the urls
wiki_urls = {}
for key, sitelink in sitelinks.items():
wiki_url = sitelink.get('url')
if wiki_url:
wiki_urls[key] = requests.utils.unquote(wiki_url)
return wiki_urls
return None


如果你运行 get_wikipedia_url_from_wikidata_id("Q182609", lang='en')你回来了: 'https://en.wikipedia.org/wiki/Jacques_Rogge'
如果你运行 get_wikipedia_url_from_wikidata_id("Q182609", lang=None)你回来了:
{'afwiki': 'https://af.wikipedia.org/wiki/Jacques_Rogge',
'alswiki': 'https://als.wikipedia.org/wiki/Jacques_Rogge',
'arwiki': 'https://ar.wikipedia.org/wiki/جاك_روج',
'azbwiki': 'https://azb.wikipedia.org/wiki/ژاک_روق',
'azwiki': 'https://az.wikipedia.org/wiki/Jak_Roqqe',
'bclwiki': 'https://bcl.wikipedia.org/wiki/Jacques_Rogge',
'bgwiki': 'https://bg.wikipedia.org/wiki/Жак_Рох',
'bnwiki': 'https://bn.wikipedia.org/wiki/জ্যাকুয়েস_রগ',
'cawiki': 'https://ca.wikipedia.org/wiki/Jacques_Rogge',
'commonswiki': 'https://commons.wikimedia.org/wiki/Category:Jacques_Rogge',
'cswiki': 'https://cs.wikipedia.org/wiki/Jacques_Rogge',
'cswikiquote': 'https://cs.wikiquote.org/wiki/Jacques_Rogge',
'cywiki': 'https://cy.wikipedia.org/wiki/Jacques_Rogge',
'dawiki': 'https://da.wikipedia.org/wiki/Jacques_Rogge',
'dewiki': 'https://de.wikipedia.org/wiki/Jacques_Rogge',
'elwiki': 'https://el.wikipedia.org/wiki/Ζακ_Ρογκ',
'enwiki': 'https://en.wikipedia.org/wiki/Jacques_Rogge',
'eowiki': 'https://eo.wikipedia.org/wiki/Jacques_Rogge',
'eswiki': 'https://es.wikipedia.org/wiki/Jacques_Rogge',
'etwiki': 'https://et.wikipedia.org/wiki/Jacques_Rogge',
'fawiki': 'https://fa.wikipedia.org/wiki/ژاک_روگ',
'fiwiki': 'https://fi.wikipedia.org/wiki/Jacques_Rogge',
'frwiki': 'https://fr.wikipedia.org/wiki/Jacques_Rogge',
'hewiki': "https://he.wikipedia.org/wiki/ז'אק_רוג",
'hrwiki': 'https://hr.wikipedia.org/wiki/Jacques_Rogge',
'huwiki': 'https://hu.wikipedia.org/wiki/Jacques_Rogge',
'idwiki': 'https://id.wikipedia.org/wiki/Jacques_Rogge',
'itwiki': 'https://it.wikipedia.org/wiki/Jacques_Rogge',
'itwikiquote': 'https://it.wikiquote.org/wiki/Jacques_Rogge',
'jawiki': 'https://ja.wikipedia.org/wiki/ジャック・ロゲ',
'kkwiki': 'https://kk.wikipedia.org/wiki/Жак_Рогге',
'kowiki': 'https://ko.wikipedia.org/wiki/자크_로게',
'ltwiki': 'https://lt.wikipedia.org/wiki/Jacques_Rogge',
'lvwiki': 'https://lv.wikipedia.org/wiki/Žaks_Roge',
'mkwiki': 'https://mk.wikipedia.org/wiki/Жак_Рог',
'mnwiki': 'https://mn.wikipedia.org/wiki/Жак_Рогге',
'mswiki': 'https://ms.wikipedia.org/wiki/Jacques_Rogge',
'nlwiki': 'https://nl.wikipedia.org/wiki/Jacques_Rogge',
'nowiki': 'https://no.wikipedia.org/wiki/Jacques_Rogge',
'plwiki': 'https://pl.wikipedia.org/wiki/Jacques_Rogge',
'ptwiki': 'https://pt.wikipedia.org/wiki/Jacques_Rogge',
'rowiki': 'https://ro.wikipedia.org/wiki/Jacques_Rogge',
'ruwiki': 'https://ru.wikipedia.org/wiki/Рогге,_Жак',
'ruwikinews': 'https://ru.wikinews.org/wiki/Категория:Жак_Рогге',
'scowiki': 'https://sco.wikipedia.org/wiki/Jacques_Rogge',
'simplewiki': 'https://simple.wikipedia.org/wiki/Jacques_Rogge',
'skwiki': 'https://sk.wikipedia.org/wiki/Jacques_Rogge',
'srwiki': 'https://sr.wikipedia.org/wiki/Жак_Рог',
'svwiki': 'https://sv.wikipedia.org/wiki/Jacques_Rogge',
'thwiki': 'https://th.wikipedia.org/wiki/ฌัก_โรคเคอ',
'tlwiki': 'https://tl.wikipedia.org/wiki/Jacques_Rogge',
'trwiki': 'https://tr.wikipedia.org/wiki/Jacques_Rogge',
'ukwiki': 'https://uk.wikipedia.org/wiki/Жак_Рогге',
'viwiki': 'https://vi.wikipedia.org/wiki/Jacques_Rogge',
'wuuwiki': 'https://wuu.wikipedia.org/wiki/雅克·罗格',
'zhwiki': 'https://zh.wikipedia.org/wiki/雅克·罗格'}

获得 Wikipedia 网址后,您还应该通过重定向来解决它们。
def get_redirect_urls(wikipedia_url_ids, retry=0, max_retry=10, backoff=2, debug=False):
import json
import requests
import time

wikipedia_url_ids_encoded = [requests.utils.quote(x) for x in wikipedia_url_ids]
request_url=r'https://en.wikipedia.org/w/api.php?action=query&titles={}&&redirects&format=json'.format("|".join(wikipedia_url_ids_encoded))
if debug: print(request_url)
response = requests.get(request_url)

if retry == max_retry:
return None

if response.status_code == 429:
# Too many requests
wait = backoff * (2 ** (retry - 1))
time.sleep(wait)
return get_redirect_urls(wikipedia_url_ids, retry=retry + 1)
response_json = json.loads(response.text)
if debug: print(response_json)
if 'query' not in response_json:
raise RuntimeError(f'impossible to parse request: {request_url}, response: {reponse_json}')
normalized = {x['from']: x['to'] for x in response_json.get('query').get('normalized', [])}
redirects = {x['from']: x['to'] for x in response_json.get('query').get('redirects', [])}

normalized_url_id_dict = {x: normalized.get(x, x) for x in wikipedia_url_ids}

return {x: redirects[normalized_url_id_dict[x]].replace(' ', '_') for x in wikipedia_url_ids
if normalized_url_id_dict[x] in redirects}

如果您删除主机名前缀并仅从 URL 路径中提取页面的标识符,您可以获得重定向 URL 的字典。
"Military_Academy_Commander_in_Chief_Hugo_Rafael_Chávez_Frías","Valley_Children’s_Hospital", 
"Park Jung-suk (video game player)", "Valley Children's Hospital",
"Troop Officers Military College",
"Hobbs_&_Shaw", "Schematic_Records", "Ethan_Klein", "Hobbs & Shaw"], debug=True)

将打印并返回:
https://en.wikipedia.org/w/api.php?action=query&titles=Tom_Cruise|Tom%20Cruise|Mark_Daniel_Gangloff|Park_Jung-suk_%28gamer%29|Military_Academy_Commander_in_Chief_Hugo_Rafael_Ch%C3%A1vez_Fr%C3%ADas|Valley_Children%E2%80%99s_Hospital|Park%20Jung-suk%20%28video%20game%20player%29|Valley%20Children%27s%20Hospital|Troop%20Officers%20Military%20College|Hobbs_%26_Shaw|Schematic_Records|Ethan_Klein|Hobbs%20%26%20Shaw&&redirects&format=json
{'batchcomplete': '', 'query': {'normalized': [{'from': 'Tom_Cruise', 'to': 'Tom Cruise'}, {'from': 'Mark_Daniel_Gangloff', 'to': 'Mark Daniel Gangloff'}, {'from': 'Park_Jung-suk_(gamer)', 'to': 'Park Jung-suk (gamer)'}, {'from': 'Military_Academy_Commander_in_Chief_Hugo_Rafael_Chávez_Frías', 'to': 'Military Academy Commander in Chief Hugo Rafael Chávez Frías'}, {'from': 'Valley_Children’s_Hospital', 'to': 'Valley Children’s Hospital'}, {'from': 'Hobbs_&_Shaw', 'to': 'Hobbs & Shaw'}, {'from': 'Schematic_Records', 'to': 'Schematic Records'}, {'from': 'Ethan_Klein', 'to': 'Ethan Klein'}], 'redirects': [{'from': 'Schematic Records', 'to': 'Intelligent dance music'}, {'from': 'Ethan Klein', 'to': 'H3h3Productions'}, {'from': "Valley Children's Hospital", 'to': 'Valley Children’s Hospital'}, {'from': 'Park Jung-suk (video game player)', 'to': 'Park Jung-suk (gamer)'}, {'from': 'Troop Officers Military College', 'to': 'Military Academy Commander in Chief Hugo Rafael Chávez Frías'}, {'from': 'Mark Daniel Gangloff', 'to': 'Mark Gangloff'}], 'pages': {'55632122': {'pageid': 55632122, 'ns': 0, 'title': 'Hobbs & Shaw'}, '43243423': {'pageid': 43243423, 'ns': 0, 'title': 'Military Academy Commander in Chief Hugo Rafael Chávez Frías'}, '3742745': {'pageid': 3742745, 'ns': 0, 'title': 'Park Jung-suk (gamer)'}, '31460': {'pageid': 31460, 'ns': 0, 'title': 'Tom Cruise'}, '63813213': {'pageid': 63813213, 'ns': 0, 'title': 'Valley Children’s Hospital'}, '49550675': {'pageid': 49550675, 'ns': 0, 'title': 'H3h3Productions'}, '81213': {'pageid': 81213, 'ns': 0, 'title': 'Intelligent dance music'}, '9316111': {'pageid': 9316111, 'ns': 0, 'title': 'Mark Gangloff'}}}}

{'Mark_Daniel_Gangloff': 'Mark_Gangloff',
'Park Jung-suk (video game player)': 'Park_Jung-suk_(gamer)',
"Valley Children's Hospital": 'Valley_Children’s_Hospital',
'Troop Officers Military College': 'Military_Academy_Commander_in_Chief_Hugo_Rafael_Chávez_Frías',
'Schematic_Records': 'Intelligent_dance_music',
'Ethan_Klein': 'H3h3Productions'}

关于python-2.7 - 如何从 Wikidata Id 获取 Wikipedia 页面?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/37079989/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com