Парсинг сайта

import requests
from bs4 import BeautifulSoup, SoupStrainer
from itertools import groupby
class TRaCAse:
    url='http://corp.fastsite.ru/'
    file = open('links.txt', 'w')
    req = requests.get(url)
    soup = BeautifulSoup(req.content, 'html.parser', parse_only=SoupStrainer('a'))
    list_1= ([link['href'] for link in soup if link.has_attr('href')])
    list_1 = list(set(list_1))
    deleted = 0
    for i in range(len(list_1)):
        if "https" not in list_1[i - deleted] :
            if "http" not in list_1[i - deleted] :
                if "www" not in list_1[i - deleted] :
                    del list_1[i - deleted]
                    deleted += 1
    ##удаление повтор. ссылок
    new_t = [el for el, _ in groupby(list_1)]
    string_x = ''.join(str(e) + '\n' for e in new_t)
    file.write(string_x)
    file.close()

url = 'http://corp.fastsite.ru/'
resp = requests.get(url)
tree = lxml.html.fromstring(resp.text)
 
xpath = './/a[(starts-with(@href,"http") or starts-with(@href,"https")) and contains(@href,"www")]/@href'
links = set(tree.xpath(xpath)) # set удалит дубликаты
print(links)
 
# или так
links = tree.xpath('.//a[@href]/@href')
links = set([href for href in links if re.match(r'(https?)://(?=www)',href)])
print(links)