Topic: How to find threads with pairs of users? (Read 236 times)

from typing import List
from collections import defaultdict
import requests
from bs4 import BeautifulSoup
import time
import sys

class Thread:
    def __init__(self, uids: List[int]) -> None:
        assert len(uids) > 0, 'you must pass a list of UIDs as input'
        self.uids_to_check = uids
        self.threads = defaultdict(set)
        self.common_threads = set()
        self.first = True
        for uid in uids:
            self.get_threads(uid)
            self.find_intersection(uid)
            self.first = False
        for threadId in self.common_threads:
            print(threadId)
        
        

        pass

    def get_threads(self, uid: int) -> None:
        start_post = 0
        prev_start_post =  float('-inf')
        while prev_start_post < start_post:
            url = 'https://bitcointalk.org/index.php?action=profile;u={};sa=showPosts;start={}'.format(str(uid),start_post)
            content = requests.get(url).content
            parsed = BeautifulSoup(content, 'html.parser')
            posts = parsed.find_all('td', class_='middletext')
            for i in range(0, len(posts), 2):
                post = posts[i]
                thread_id = int(str(post.find_all('a')[-1]).split('"')[1].split('topic=')[1].split('.')[0])
                self.threads[uid].add(thread_id)
            url = str(parsed.find_all('a', class_='navPages')[-1]).split('"')[-2]
            prev_start_post = start_post
            start_post = int(url.split('start=')[-1])
            time.sleep(1)
        return None

    def find_intersection(self, uid:int) -> None:
        if self.first:
            for threadID in self.threads[uid]:
                self.common_threads.add(threadID)
            return None
        new_common_threads = set()
        for threadID in self.threads[uid]:
            if threadID in self.common_threads:
                new_common_threads.add(threadID)
        self.common_threads = new_common_threads

        return None

if __name__ == '__main__':
    uids = sys.argv[1:]
    uids = [int(x) for x in uids]
    res = Thread(uids)

2181
325
1735
383
43
652
1931
241
2162
338
1013
342
567
632
1976
1786
1790
671

comm -12 <(wget -qO- https://loyce.club/archive/members/45/459836.html | grep '' | cut -d'=' -f4 | cut -d'.' -f1 | sort -u) <(wget -qO- https://loyce.club/archive/members/6/65837.html | grep '' | cut -d'=' -f4 | cut -d'.' -f1 | sort -u) | sort -n | sed s/^/'https:\/\/bitcointalk.org\/index.php?topic='/