API:Parsing wikitext
(Redirected from API:Parse)
 | This page is part of the MediaWiki Action API documentation. |
GET/POST request to parse content of a page and obtain the output.
API documentation
[edit]
Example 1: Parse content of a page
[edit]GET request
[edit]Response
[edit]{
"parse": {
"title": "Pet door",
"pageid": 3276454,
"revid": 852892138,
"text": {
"*": "<div class=\"mw-parser-output\"><div class=\"thumb tright\"><div class=\"thumbinner\" style=\"width:222px;\"><a href=\"/wiki/File:Doggy_door_exit.JPG\" class=\"image\"><img alt=\"\" src=\"//upload.wikimedia.org/wikipedia/commons/thumb/7/71/Doggy_door_exit.JPG/220px-Doggy_door_exit.JPG\" width=\"220\" height=\"165\" class=\"thumbimage\" srcset=\"//upload.wikimedia.org/wikipedia/commons/thumb/7/71/Doggy_door_exit.JPG/330px-Doggy_door_exit.JPG 1.5x,
...
}
}
}
Sample code
[edit]Python
[edit]#!/usr/bin/python3
"""
parse.py
MediaWiki API Demos
Demo of `Parse` module: Parse content of a page
MIT License
"""
import requests
S = requests.Session()
URL = "https://en.wikipedia.org/w/api.php"
PARAMS = {
"action": "parse",
"page": "Pet door",
"format": "json"
}
R = S.get(url=URL, params=PARAMS)
DATA = R.json()
print(DATA["parse"]["text"]["*"])
PHP
[edit]<?php
/*
parse.php
MediaWiki API Demos
Demo of `Parse` module: Parse content of a page
MIT License
*/
$endPoint = "https://en.wikipedia.org/w/api.php";
$params = [
"action" => "parse",
"page" => "Pet door",
"format" => "json"
];
$url = $endPoint . "?" . http_build_query( $params );
$ch = curl_init( $url );
curl_setopt( $ch, CURLOPT_RETURNTRANSFER, true );
$output = curl_exec( $ch );
curl_close( $ch );
$result = json_decode( $output, true );
echo( $result["parse"]["text"]["*"] );
JavaScript
[edit]/**
* parse.js
*
* MediaWiki API Demos
* Demo of `Parse` module: Parse content of a page
*
* MIT License
*/
const url = "https://en.wikipedia.org/w/api.php?" +
new URLSearchParams({
origin: "*",
action: "parse",
page: "Pet door",
format: "json",
});
try {
const req = await fetch(url);
const json = await req.json();
console.log(json.parse.text["*"]);
} catch (e) {
console.error(e);
}
MediaWiki JS
[edit]/**
* parse.js
*
* MediaWiki API Demos
* Demo of `Parse` module: Parse content of a page
* MIT License
*/
const params = {
action: 'parse',
page: 'Pet door',
format: 'json'
};
const api = new mw.Api();
api.get(params).done(data => {
console.log(data.parse.text['*']);
});
Example 2: Parse a section of a page and fetch its table data
[edit]GET request
[edit]api.php?
Response
[edit]| Response |
|---|
{
"parse": {
"title": "Wikipedia:Unusual articles/Places and infrastructure",
"pageid": 38664530,
"wikitext": {
"*": "===Antarctica===\n<!--[[File:Grytviken church.jpg|thumb|150px|right|A little church in [[Grytviken]] in the [[Religion in Antarctica|Antarctic]].]]-->\n{| class=\"wikitable\"\n|-\n| '''[[Emilio Palma]]'''\n| An Argentine national who is the first person known to be born on the continent of Antarctica.\n|-\n| '''[[Scouting in the Antarctic]]'''\n| Always be prepared for glaciers and penguins.\n|}"
}
}
}
|
Sample code
[edit]| parse_wikitable.py |
|---|
#!/usr/bin/python3
"""
parse_wikitable.py
MediaWiki Action API Code Samples
Demo of `Parse` module: Parse a section of a page, fetch its table data and save
it to a CSV file
MIT license
"""
import csv
import requests
S = requests.Session()
URL = "https://en.wikipedia.org/w/api.php"
TITLE = "Wikipedia:Unusual_articles/Places_and_infrastructure"
PARAMS = {
'action': "parse",
'page': TITLE,
'prop': 'wikitext',
'section': 5,
'format': "json"
}
def get_table():
""" Parse a section of a page, fetch its table data and save it to a CSV file
"""
res = S.get(url=URL, params=PARAMS)
data = res.json()
wikitext = data['parse']['wikitext']['*']
lines = wikitext.split('|-')
entries = []
for line in lines:
line = line.strip()
if line.startswith("|"):
table = line[2:].split('||')
entry = table[0].split("|")[0].strip("'''[[]]\n"), table[0].split("|")[1].strip("\n")
entries.append(entry)
file = open("places_and_infrastructure.csv", "w")
writer = csv.writer(file)
writer.writerows(entries)
file.close()
if __name__ == '__main__':
get_table()
|
Possible errors
[edit]| Code | Info |
|---|---|
| missingtitle | The page you specified doesn't exist. |
| nosuchsection | There is no section section in page. |
| pagecannotexist | Namespace doesn't allow actual pages. |
| invalidparammix |
|
Parameter history
[edit]- v1.38: Introduced
showstrategykeys - v1.32: Deprecated
disabletidy - v1.31: Introduced
disablestylededuplication - v1.30: Introduced
revid,useskin,wrapoutputclass