filter.py

import argparse
import csv
import time

import requests

HEADERS = {
    'Host': 'pan.baidu.com',
    'Connection': 'keep-alive',
    'Upgrade-Insecure-Requests': '1',
    'Sec-Fetch-Dest': 'document',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'Sec-Fetch-Site': 'same-site',
    'Sec-Fetch-Mode': 'navigate',
    'Referer': 'https://pan.baidu.com',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-US;q=0.7,en-GB;q=0.6,ru;q=0.5',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
}

arg = argparse.ArgumentParser()
arg.add_argument('--start', type=int, default=1, help='start index')

args = arg.parse_args()
start = args.start
                 
f = open('23ape.csv')
g = open('result.txt', mode='a')
h = open('link.txt', mode='a')
csv_reader = csv.reader(f)

# 跳过表头
next(csv_reader)

for i, row in enumerate(csv_reader, start=1):

    if i < start:
        continue

    try:
        url, password, title = row[0], row[1], row[2]
        response = requests.get(url, headers=HEADERS)
        response.raise_for_status()
        metatdata = f'{i}.{title}'
        if '请输入提取码' in response.text:
            if '无' not in password:
                url = f'{url}&pwd={password}'

            g.write(','.join((metatdata, url)))
            g.write('\n')

            h.write(f'{url}\n')

        elif '链接不存在' in response.text:
            print(f'{i}.链接{url} 不存在')
        else:
            print(response)

        time.sleep(0.1)

    except requests.HTTPError as e:
        print(e)
        continue

    except KeyboardInterrupt:
        break

f.close()
g.close()
h.close()