之前一直使用的聚磁力最近开始收费了，当然也不贵，而且还挺好用的，支持的源也很多。
但是因为用的比较少，收费模式是包月的，所以就想找个替代品了，网上搜了下没找到其他的。
于是写了个爬虫的，跑起来没问题。
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
| import requests
from bs4 import BeautifulSoup
class MagnetApi:
def __init__(self, keyword,ilogger):
self.logger = ilogger
self.keyword = keyword
self.url = "https://clzz1053.buzz/search-" + keyword + "-1-0-1.html"
self.data_list = []
@staticmethod
def get_size(string):
if " GB" in string:
return string.replace(" GB", "")
if " MB" in string:
return "{:.2f}".format(float(string.replace(" MB", "")) / 1024)
return string
def scrape_data(self):
response = requests.get(self.url)
html_content = response.text
soup = BeautifulSoup(html_content, 'html.parser')
data_elements = soup.find_all('div', class_='ssbox')
for element in data_elements:
magnet_link = element.find('a', href=lambda href: href.startswith('magnet:?xt=urn:btih:')).get('href')
size_element = element.find('span', class_='lightColor')
size = size_element.text.strip() if size_element else ""
name = element.find('a').text.strip()
data = {
"magnet": magnet_link,
"size": size,
"name": name
}
self.data_list.append(data)
self.data_list = sorted(self.data_list, key=lambda x: float(self.get_size(x['size'])), reverse=True)
self.logger.info("Scraped data for keyword: " + self.keyword+ " and got: " + str(len(self.data_list)) + " results")
|
