SLR JAV info

slrjav.csv

slrjav.py

#!/usr/bin/env python3
# get JAV studios' info from SLR
# 2025, poontology
from random import random
from time import sleep
from lxml import html
import csv, io, re
import requests

AUTH_JWT = ''
if AUTH_JWT == '':
    print("SLR login is required to see JAV IDs")
    exit()

def slrget(path):
    headers = {
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36',
        'cookie': 'auth_jwt=' + AUTH_JWT
    }
    #print('get', path)
    return html.fromstring(requests.get('https://www.sexlikereal.com' + path, headers=headers).text)

def get_javid(vpg):
    txt = '\n'.join(vpg.xpath('//*[@id="tabs-about"]//text()')).strip()
    try:
      return re.findall(r"JAV ID: ([^ ]+)", txt).pop()
    except IndexError:
      pass

def get_actual_vidcount(spg):
    txt = '\n'.join(spg.find_class('c-meta--studio')[0].xpath('.//text()')).strip()
    try:
      return re.findall(r"(\d+) videos", txt).pop()
    except IndexError:
      pass


if __name__ == '__main__':
    fn = 'slrjav.csv'
    csvr = csv.DictReader(open(fn))
    stud = {row['path']: row for row in csvr}

    for u,s in stud.items():
        spg = slrget(u + '?sort=most_recent')
        s['actual_vidcount'] = get_actual_vidcount(spg)
        if u == '/studios/3dvr': print(s)
        if len(s['javcodes']) > 0: continue
        vpg = slrget(spg.xpath('//*[@data-qa="scenes-grid-item-media"]/a')[0].attrib['href'])
        s['javcodes'] = get_javid(vpg)
        if s['javcodes'] is None: print('no javid:', s)
        print('.', end='', flush=True)
        sleep(1.5 + random())

    fh = open(fn, 'w')
    fn = ['name', 'path', 'vidcount', 'actual_vidcount', 'javcodes']
    csvw = csv.DictWriter(fh, fieldnames=fn)
    csvw.writeheader()
    for k,v in sorted(stud.items()):
        v['path'] = k
        csvw.writerow(v)