Created
May 31, 2018 15:59
-
-
Save sinanatra/cd7c503c9dc8dde5f85041593e1e6eae to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import codecs | |
import urllib, re | |
import requests | |
import urllib.request | |
import datetime | |
import lxml.html | |
import os | |
import time | |
from bs4 import BeautifulSoup as soup | |
ID = "Q36180" | |
if not os.path.exists("img"): | |
os.makedirs("img") | |
url = "https://www.wikidata.org/wiki/"+ID | |
print(url) | |
html = lxml.html.parse(urllib.request.urlopen(url) ) | |
links = [i.strip() for i in html.xpath("//span[contains(@class, 'wikibase-sitelinkview-page')]/a/@href")] | |
num = 0 | |
for link in links: | |
print (link) | |
response = requests.get(link) | |
soup = BeautifulSoup(response.text, 'html.parser') | |
img_tags = soup.find_all('img') | |
urls = [img['src'] for img in img_tags] | |
for url in urls: | |
try: | |
if url.endswith('jpg'): | |
load_img = urllib.request.urlretrieve("http:"+url,"img/"+ID+str(num)+".jpg") | |
elif url.endswith('png'): | |
load_img = urllib.request.urlretrieve("http:"+test,"url/"+ID+str(num)+".png") | |
elif test.endswith('svg'): | |
continue | |
elif url.endswith('gif'): | |
load_img = urllib.request.urlretrieve("http:"+test,"url/"+ID+str(num)+".gif") | |
num +=1 | |
except Exception as e: | |
#print (e) | |
continue | |
print("That's All Folks!") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment