forked from phito/darknet_diaries_llm
13 lines
373 B
Python
13 lines
373 B
Python
|
import requests
|
||
|
|
from bs4 import BeautifulSoup
|
||
|
|
|
||
|
|
for i in range(1, 139):
|
||
|
|
url = f"https://darknetdiaries.com/transcript/{i}"
|
||
|
|
r = requests.get(url)
|
||
|
|
soup = BeautifulSoup(r.text, 'html.parser')
|
||
|
|
pre_section = soup.find('pre')
|
||
|
|
|
||
|
|
if pre_section:
|
||
|
|
text = pre_section.get_text()
|
||
|
|
with open(f"data/episode_{i}.txt", "w") as f:
|
||
|
|
f.write(text)
|