Created
July 4, 2020 02:40
-
-
Save gandroz/f4cc5ca52b3c2e84abf28e8a73bc708e to your computer and use it in GitHub Desktop.
Scrap the tag and number of claps of popular articles on medium
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
from bs4 import BeautifulSoup | |
import requests | |
def convert_to_num(s): | |
if isinstance(s, int): | |
return s | |
elif 'K' in s: | |
return int(1000 * float(s.replace('K',''))) | |
else: | |
return int(s) | |
for post in posts: | |
post['tag'] = [] | |
post['claps'] = -1 | |
try: | |
r = requests.get(post['url']) | |
except: | |
print(post['url']) | |
continue | |
soup = BeautifulSoup(r.text) | |
# tags | |
hrefs = soup.findAll('a', href=True) | |
for href in hrefs: | |
res = re.search("^/tagged/(.*)", href['href']) | |
if res: | |
post['tag'].append(res.group(1)) | |
# claps | |
buttons = soup.findAll('button') | |
for i, button in enumerate(buttons): | |
res = re.search("(.*) claps", button.text) | |
if res: | |
post['claps'] = convert_to_num(res.group(1)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment