File size: 3,541 Bytes
942b6ab |
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 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
import time
import aiohttp
from bs4 import BeautifulSoup
from helper.html_scraper import Scraper
from constants.base_url import GLODLS
class Glodls:
def __init__(self):
self.BASE_URL = GLODLS
self.LIMIT = None
def _parser(self, htmls):
try:
for html in htmls:
soup = BeautifulSoup(html, "html.parser")
my_dict = {"data": []}
for tr in soup.find_all("tr", class_="t-row")[0:-1:2]:
td = tr.find_all("td")
name = td[1].find_all("a")[-1].find("b").text
url = self.BASE_URL + td[1].find_all("a")[-1]["href"]
torrent = self.BASE_URL + td[2].find("a")["href"]
magnet = td[3].find("a")["href"]
size = td[4].text
seeders = td[5].find("font").find("b").text
leechers = td[6].find("font").find("b").text
try:
uploader = td[7].find("a").find("b").find("font").text
except:
uploader = ""
my_dict["data"].append(
{
"name": name,
"size": size,
"uploader": uploader,
"seeders": seeders,
"leechers": leechers,
"magnet": magnet,
"torrent": torrent,
"url": self.BASE_URL + url,
}
)
if len(my_dict["data"]) == self.LIMIT:
break
try:
pagination = soup.find("div", class_="pagination")
total_pages = pagination.find_all("a")[-2]["href"]
total_pages = total_pages.split("=")[-1]
my_dict["total_pages"] = int(total_pages) + 1
except:
...
return my_dict
except:
return None
async def search(self, query, page, limit):
async with aiohttp.ClientSession() as session:
start_time = time.time()
self.LIMIT = limit
url = (
self.BASE_URL
+ "/search_results.php?search={}&cat=0&incldead=0&inclexternal=0&lang=0&sort=seeders&order=desc&page={}".format(
query, page - 1
)
)
return await self.parser_result(start_time, url, session)
async def parser_result(self, start_time, url, session):
html = await Scraper().get_all_results(session, url)
results = self._parser(html)
if results is not None:
results["time"] = time.time() - start_time
results["total"] = len(results["data"])
return results
return results
async def trending(self, category, page, limit):
async with aiohttp.ClientSession() as session:
start_time = time.time()
self.LIMIT = limit
url = self.BASE_URL + "/today.php"
return await self.parser_result(start_time, url, session)
async def recent(self, category, page, limit):
async with aiohttp.ClientSession() as session:
start_time = time.time()
self.LIMIT = limit
url = self.BASE_URL + "/search.php"
return await self.parser_result(start_time, url, session) |