Wikipedia-API 0.3.3

Python Wrapper for Wikipedia

Wikipedia API

This package provides python API for accessing Wikipedia.

Installation

pip3 install wikipedia-api

Usage

import wikipediaapi

# Extract data in Wiki format
wiki_wiki = wikipediaapi.Wikipedia('en')

page_py = wiki_wiki.page('Python_(programming_language)')

print("Page - Exists: %s" % page_py.exists())
# Page - Exists: True

print("Page - Id: %s" % page_py.pageid)
# Page - Id: 23862

print("Page - Title: %s" % page_py.title)
# Page - Title: Python (programming language)

print("Page - Summary: %s" % page_py.summary[0:60])
# Page - Summary: Python is a widely used high-level programming language for

def print_sections(sections, level=0):
        for s in sections:
                print("%s: %s - %s" % ("*" * (level + 1), s.title, s.text[0:40]))
                print_sections(s.sections, level + 1)


print_sections(page_py.sections)
# *: History - Python was conceived in the late 1980s,
# *: Features and philosophy - Python is a multi-paradigm programming l
# *: Syntax and semantics - Python is meant to be an easily readable
# **: Indentation - Python uses whitespace indentation, rath
# **: Statements and control flow - Python's statements include (among other
# **: Expressions - Some Python expressions are similar to l
# ...

def print_langlinks(page):
        langlinks = page.langlinks
        for k in sorted(langlinks.keys()):
            v = langlinks[k]
            print("%s: %s - %s: %s" % (k, v.language, v.title, v.fullurl))

print_langlinks(page_py)
# af: af - Python (programmeertaal): https://af.wikipedia.org/wiki/Python_(programmeertaal)
# als: als - Python (Programmiersprache): https://als.wikipedia.org/wiki/Python_(Programmiersprache)
# an: an - Python: https://an.wikipedia.org/wiki/Python
# ar: ar - بايثون: https://ar.wikipedia.org/wiki/%D8%A8%D8%A7%D9%8A%D8%AB%D9%88%D9%86
# as: as - পাইথন: https://as.wikipedia.org/wiki/%E0%A6%AA%E0%A6%BE%E0%A6%87%E0%A6%A5%E0%A6%A8
# ...

def print_links(page):
        links = page.links
        for title in sorted(links.keys()):
            print("%s: %s" % (title, links[title]))

print_links(page_py)
# 3ds Max: 3ds Max (id: ??, ns: 0)
# ?:: ?: (id: ??, ns: 0)
# ABC (programming language): ABC (programming language) (id: ??, ns: 0)
# ALGOL 68: ALGOL 68 (id: ??, ns: 0)
# Abaqus: Abaqus (id: ??, ns: 0)
# ...

def print_categories(page):
        categories = page.categories
        for title in sorted(categories.keys()):
            print("%s: %s" % (title, categories[title]))


print("Categories")
print_categories(page_py)
# Category:All articles containing potentially dated statements: ...
# Category:All articles with unsourced statements: ...
# Category:Articles containing potentially dated statements from August 2016: ...
# Category:Articles containing potentially dated statements from March 2017: ...
# Category:Articles containing potentially dated statements from September 2017: ...
# ...

section_py = page_py.section_by_title('Features and philosophy')
print("Section - Title: %s" % section_py.title)
# Section - Title: Features and philosophy

print("Section - Text: %s" % section_py.text[0:60])
# Section - Text: Python is a multi-paradigm programming language. Object-orie

# Now lets extract texts with HTML tags
wiki_html = wikipediaapi.Wikipedia(
        language='cs',
        extract_format=wikipediaapi.ExtractFormat.HTML
)

page_ostrava = wiki_html.page('Ostrava')
print("Page - Summary: %s" % page_ostrava.summary[0:60])
# Page - Summary: <p><b>Ostrava</b> (polsky <span lang="pl" title="polština" x

page_nonexisting = wiki_wiki.page('Wikipedia-API-FooBar')
print("Page - Exists: %s" % page_nonexisting.exists())
# Page - Exists: False

print("Page - Id: %s" % page_nonexisting.pageid)
# Page - Id: -1

# Create wikipedia for Germany
wiki_de = wikipediaapi.Wikipedia('de')
de_page = wiki_de.page('Deutsche Sprache')
print(de_page.title + ": " + de_page.fullurl)
# Deutsche Sprache: https://de.wikipedia.org/wiki/Deutsche_Sprache
print(de_page.summary[0:60])
# Die deutsche Sprache bzw. Deutsch [dɔʏ̯t͡ʃ], abgekürzt Dt. o

# But you can still fetch data from english version
en_page = de_page.langlinks['en']
print(en_page.title + ": " + en_page.fullurl)
# German language: https://en.wikipedia.org/wiki/German_language
print(en_page.summary[0:60])
# German (Deutsch [ˈdɔʏt͡ʃ] ( listen)) is a West Germanic lang

External Links

• GitHub

• PyPi

• Travis

• ReadTheDocs

Changelog

0.3.3

• Added support for request timeout

• Add header: Accept-Encoding: gzip

0.3.2

• Added support for property Categories

0.3.1

• Removing WikipediaLangLink

• Page keeps track of its own language, so it’s easier to jump between different translations of the same page

0.3.0

• Rename directory from wikipedia to wikipediaapi to avoid collisions

0.2.4

• Handle redirects properly

0.2.3

• Usage method page instead of article in Wikipedia

0.2.2

• Added support for property Links

0.2.1

• Added support for property Langlinks

0.2.0

• Use properties instead of functions

• Added support for property Info

0.1.6

• Support for extracting texts with HTML markdown

• Added initial version of unit tests

0.1.4

• It’s possible to extract summary and sections of the page

• Added support for property Extracts