Last active
January 20, 2022 21:49
-
-
Save froop/c14ebf8192040499b986d0a927ad4a57 to your computer and use it in GitHub Desktop.
[Python] Web scraping sample
This file contains hidden or 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 requests | |
import os | |
from bs4 import BeautifulSoup | |
RES_PATH = 'result' # 結果出力先パス | |
os.makedirs(RES_PATH, exist_ok=True) | |
root_page = requests.get('https://github.com/froop?tab=repositories') | |
root_soup = BeautifulSoup(root_page.text, 'html.parser') | |
repo_list = root_soup.find(id='user-repositories-list') | |
for item in repo_list.find_all('a', attrs={'itemprop': 'name codeRepository'}): | |
item_name = item.text.strip() | |
print(item_name + ': ' + item.get('href')) | |
item_page = requests.get('https://github.com' + item.get('href')) | |
item_soup = BeautifulSoup(item_page.text, 'html.parser') | |
readme = item_soup.find(id='readme') | |
if not hasattr(readme, 'text'): | |
continue | |
with open(RES_PATH + '/' + item_name + '.txt', mode='w', encoding='utf-8') as f: | |
f.write(readme.text) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment