wikipediaからのページからリンク一覧を取得する方法 ref: https://qiita.com/tadaken3/items/e09ba2ede988bbacb303

file0.txt

#codeing:utf-8

import re
from bs4 import BeautifulSoup
from urllib.request import urlopen
from urllib.parse import unquote

url = "https://ja.wikipedia.org/wiki/%E3%83%86%E3%82%A4%E3%83%AB%E3%82%BA_%E3%82%AA%E3%83%96_%E3%82%A4%E3%83%8E%E3%82%BB%E3%83%B3%E3%82%B9"

html = urlopen(url)
bsObj = BeautifulSoup(html,'html.parser')

pattern = re.compile("^(/wiki/)((?!:).)*$")

for link in bsObj.find('div',{'id':'bodyContent'}).findAll('a',href = pattern):
    if 'href' in link.attrs:
        print (unquote(link.attrs['href']))     

wiki_crawier.py

#codeing:utf-8

import re
from bs4 import BeautifulSoup
from urllib.request import urlopen
from urllib.parse import unquote

url = "https://ja.wikipedia.org/wiki/%E3%83%86%E3%82%A4%E3%83%AB%E3%82%BA_%E3%82%AA%E3%83%96_%E3%82%A4%E3%83%8E%E3%82%BB%E3%83%B3%E3%82%B9"

html = urlopen(url)
bsObj = BeautifulSoup(html,'html.parser')

pattern = re.compile("^(/wiki/)((?!:).)*$")

for link in bsObj.find('div',{'id':'bodyContent'}).findAll('a',href = pattern):
    if 'href' in link.attrs:
        print (unquote(link.attrs['href']))