Hello I am trying to make a scraper that saves all .css files from a web page in a folder but when running my script I get this error:
with open(shit, 'wb') as f: FileNotFoundError: [Errno 2] No such file or directory: 'https://url.com/cache/themes/theme1/index.min.css'
And here is my code:
from bs4 import BeautifulSoup
import requests
import os
proxies = {
'http': 'socks5h://127.0.0.1:9050',
'https': 'socks5h://127.0.0.1:9050'
}
url = "https://url.com"
folder = "Files"
resp = requests.get(url, proxies=proxies)
soup = BeautifulSoup(resp.text, features='lxml')
def Downloader(url, folder):
os.mkdir(os.path.join(os.getcwd(), folder))
os.chdir(os.path.join(os.getcwd(), folder))
css = soup.find_all('link', rel="stylesheet")
for cum in css:
shit = cum['href']
if "http://" in shit:
with open(shit, 'wb') as f:
piss = requests.get(shit, proxies=proxies)
f.write(piss.content)
Downloader(url=url, folder=folder)
Does anyone know what the issue might be? Thank you <3
CodePudding user response:
You are trying to write to file with a name that has /
in it. This identifies it as part a directory/folder. So either remove/replace those, or build in the logic that creates those folders structure, and it'll write to file.
import requests
from bs4 import BeautifulSoup
import os
proxies = {
'http': 'socks5h://127.0.0.1:9050',
'https': 'socks5h://127.0.0.1:9050'
}
url = "https://url.com"
folder = "Files"
resp = requests.get(url, proxies=proxies)
soup = BeautifulSoup(resp.text, features='lxml')
def Downloader(url, folder):
try:
os.mkdir(os.path.join(os.getcwd(), folder))
except Exception as e:
print(e)
os.chdir(os.path.join(os.getcwd(), folder))
css = soup.find_all('link', rel="stylesheet")
for each in css:
href = each['href']
if "http://" in href or "https://" in href:
filename = href.split('//')[-1].replace('/','_').replace('.','_')
with open(filename, 'wb') as f:
response = requests.get(href, proxies=proxies)
f.write(response.content)
Downloader(url=url, folder=folder)