mirror of
https://codeberg.org/hyperreal/print-wp-sources
synced 2025-01-18 14:23:45 +01:00
21 lines
463 B
Python
21 lines
463 B
Python
|
import sys
|
||
|
|
from urllib.request import urlopen
|
||
|
|
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
if len(sys.argv) != 2:
|
||
|
|
exit("Usage: dl_wp_pdf ARTICLE_NAME")
|
||
|
|
article = sys.argv[1]
|
||
|
|
|
||
|
|
url = f"https://en.wikipedia.org/wiki/{article}"
|
||
|
|
text = urlopen(url).read()
|
||
|
|
soup = BeautifulSoup(text, "html.parser")
|
||
|
|
for link in soup.find_all("a", attrs={"class": "external text"}):
|
||
|
|
print(link.get("href"))
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|