def start_datascraper(session, board_name, site_name, link_type, choice_type=None):
print("Scrape Processing")
info = link_check(session, board_name)
if not info["exists"]:
return [False, info]
print("Board: " + board_name)
array = scrape_choice(board_name)
pool = multiprocessing()
threads = board_scraper(session, array[0], "")
archive_threads = board_scraper(session, array[1], "archive")
threads = threads + archive_threads
print("Original Count: "+str(len(threads)))
formatted_directories = main_helper.format_directories(
j_directory, site_name, board_name)
model_directory = formatted_directories["model_directory"]
metadata_directory = formatted_directories["metadata_directory"]
api_directory = formatted_directories["api_directory"]
directory = model_directory
print("Scraping Threads")
threads = pool.starmap(thread_scraper,
product(threads, [board_name], [session], [directory]))
threads = [x for x in threads if x is not None]
post_count = len(threads)
print("Valid Count: "+str(post_count))
print("Downloading Media")
count_results = str(len([x for x in threads if x is None]))
print("Invalid Count: "+count_results)
num = random.randrange(0, 200)
avatar = f"https://s.4cdn.org/image/title/{num}.png"
link = info["link"]
info["download"] = prepare_download.start(
username=board_name, link=link, image_url=avatar, post_count=post_count, webhook=webhook)
info["download"].others.append([threads, session, directory, board_name])
# When profile is done scraping, this function will return True
return [True, info]
def start_datascraper(api, identifier, site_name, choice_type=None):
print("Scrape Processing")
subscription = api.get_subscription(identifier)
if not subscription:
return [False, subscription]
post_count = subscription.postsCount
user_id = str(subscription.id)
avatar = subscription.avatar
username = subscription.username
link = subscription.link
formatted_directories = main_helper.format_directories(
j_directory, site_name, username)
metadata_directory = formatted_directories["metadata_directory"]
archive_path = os.path.join(metadata_directory, "Mass Messages.json")
if subscription.is_me:
imported = import_archive(archive_path)
mass_messages = api.get_mass_messages(resume=imported)
export_archive(mass_messages, archive_path,
json_settings, rename=False)
info = {}
info["download"] = prepare_download.start(
username=username, link=link, image_url=avatar, post_count=post_count, webhook=webhook)
print("Name: "+username)
api_array = scrape_choice(api, subscription)
api_array = format_options(api_array, "apis")
apis = api_array[0]
api_string = api_array[1]
if not json_settings["auto_scrape_apis"]:
print("Apis: "+api_string)
value = int(input().strip())
else:
value = 0
if value:
apis = [apis[value]]
else:
apis.pop(0)
for item in apis:
print("Type: "+item["api_type"])
only_links = item["api_array"]["only_links"]
post_count = str(item["api_array"]["post_count"])
item["api_array"]["username"] = username
item["api_array"]["subscription"] = subscription
api_type = item["api_type"]
results = prepare_scraper(
api, site_name, item)
print
if any(x for x in subscription.scraped):
subscription.download_info["directory"] = j_directory
subscription.download_info["model_directory"] = os.path.join(
j_directory, username)
subscription.download_info["webhook"] = webhook
print("Scrape Completed"+"\n")
return [True, info]
def paid_content_scraper(api):
paid_contents = api.get_paid_content(refresh=False)
results = []
for paid_content in paid_contents:
author = paid_content.get("author")
author = paid_content.get("fromUser", author)
subscription = create_subscription(author)
subscription.sessions = api.sessions
subscription.download_info["directory"] = j_directory
username = subscription.username
model_directory = os.path.join(j_directory, username)
metadata_folder = os.path.join(model_directory, "Metadata")
api_type = paid_content["responseType"].capitalize()+"s"
metadata_path = os.path.join(
metadata_folder, api_type+".json")
site_name = "OnlyFans"
media_type = format_media_types()
formatted_directories = main_helper.format_directories(
j_directory, site_name, username, media_type, api_type)
new_item = media_scraper([paid_content], api,
formatted_directories, username, api_type)
for directory in new_item["directories"]:
os.makedirs(directory, exist_ok=True)
download_metadata = prepare_metadata(new_item).metadata
subscription.set_scraped(api_type, download_metadata)
metadata = prepare_metadata(new_item, export=True).metadata
metadata = jsonpickle.encode(
metadata, unpicklable=False)
new_metadata = jsonpickle.decode(metadata)
old_metadata = import_archive(metadata_path)
if old_metadata:
old_metadata = metadata_fixer(directory=metadata_path.replace(
".json", ""), metadata_types=old_metadata)
unrefined = compare_metadata(
new_metadata, old_metadata, new_chain=True)
unrefined = prepare_metadata(unrefined, export=True).metadata
new_metadata = jsonpickle.encode(
unrefined, unpicklable=False)
new_metadata = jsonpickle.decode(new_metadata)
results.append(new_metadata)
os.makedirs(model_directory, exist_ok=True)
a = export_archive(new_metadata, metadata_path, json_settings)
x = download_media(api, subscription)
return results
def prepare_scraper(sessions, site_name, item):
api_type = item["api_type"]
api_array = item["api_array"]
link = api_array["api_link"]
locations = api_array["media_types"]
username = api_array["username"]
directory = api_array["directory"]
api_count = api_array["post_count"]
master_set = []
media_set = []
metadata_set = []
pool = multiprocessing()
formatted_directories = main_helper.format_directories(
j_directory, site_name, username, locations, api_type)
model_directory = formatted_directories["model_directory"]
metadata_directory = formatted_directories["metadata_directory"]
api_directory = formatted_directories["api_directory"]
if api_type == "Posts":
ceil = math.ceil(api_count / 100)
a = list(range(ceil))
for b in a:
b = b * 100
master_set.append(link.replace("offset=0", "offset=" + str(b)))
if api_type == "Archived":
ceil = math.ceil(api_count / 100)
a = list(range(ceil))
for b in a:
b = b * 100
master_set.append(link.replace("offset=0", "offset=" + str(b)))
if api_type == "Stories":
master_set.append(link)
if api_type == "Highlights":
r = main_helper.json_request(sessions[0], link)
if "error" in r:
return
for item in r["list"]:
link2 = "https://stars.avn.com/api2/v2/stories/collections/" + \
str(item["id"])
master_set.append(link2)
master_set2 = main_helper.assign_session(master_set, sessions)
media_set = {}
media_set["set"] = []
media_set["found"] = False
count = len(master_set2)
max_attempts = 100
for attempt in list(range(max_attempts)):
print("Scrape Attempt: " + str(attempt + 1) + "/" + str(max_attempts))
media_set2 = pool.starmap(
media_scraper,
product(master_set2, [sessions], [formatted_directories],
[username], [api_type]))
media_set["set"].extend(media_set2)
faulty = [x for x in media_set2 if not x]
if not faulty:
print("Found: " + api_type)
media_set["found"] = True
break
else:
if count < 2:
break
num = len(faulty) * 100
print("Missing " + str(num) + " Posts... Retrying...")
master_set2 = main_helper.restore_missing_data(
master_set2, media_set2)
if not media_set["found"]:
print("No " + api_type + " Found.")
media_set = media_set["set"]
main_helper.delete_empty_directories(api_directory)
media_set = [x for x in media_set]
media_set = main_helper.format_media_set(media_set)
metadata_set = media_set
if export_metadata:
metadata_set = [x for x in metadata_set if x["valid"] or x["invalid"]]
for item in metadata_set:
if item["valid"] or item["invalid"]:
legacy_metadata = formatted_directories["legacy_metadata"]
if delete_legacy_metadata:
if os.path.isdir(legacy_metadata):
shutil.rmtree(legacy_metadata)
if metadata_set:
os.makedirs(metadata_directory, exist_ok=True)
archive_directory = os.path.join(metadata_directory, api_type)
metadata_set_copy = copy.deepcopy(metadata_set)
metadata_set = main_helper.filter_metadata(metadata_set_copy)
main_helper.export_archive(metadata_set, archive_directory,
json_settings)
return [media_set, directory]
def prepare_scraper(sessions, site_name, item):
api_type = item["api_type"]
api_array = item["api_array"]
link = api_array["api_link"]
locations = api_array["media_types"]
username = api_array["username"]
directory = api_array["directory"]
api_count = api_array["post_count"]
master_set = []
media_set = []
metadata_set = []
pool = ThreadPool()
formatted_directories = main_helper.format_directories(
j_directory, site_name, username, locations, api_type)
model_directory = formatted_directories["model_directory"]
api_directory = formatted_directories["api_directory"]
metadata_directory = formatted_directories["metadata_directory"]
legacy_metadata_directory = os.path.join(api_directory, "Metadata")
# legacy_metadata = main_helper.legacy_metadata(legacy_metadata_directory)
if api_type == "Profile":
profile_scraper(link, sessions[0], directory, username)
return
if api_type == "Posts":
num = 100
link = link.replace("limit=0", "limit="+str(num))
original_link = link
ceil = math.ceil(api_count / num)
a = list(range(ceil))
for b in a:
b = b * num
master_set.append(link.replace(
"offset=0", "offset=" + str(b)))
if api_type == "Archived":
ceil = math.ceil(api_count / 100)
a = list(range(ceil))
for b in a:
b = b * 100
master_set.append(link.replace(
"offset=0", "offset=" + str(b)))
def xmessages(link):
f_offset_count = 0
while True:
y = main_helper.json_request(sessions[0], link)
if not y:
return
if "list" in y:
if y["list"]:
master_set.append(link)
if y["hasMore"]:
f_offset_count2 = f_offset_count+100
f_offset_count = f_offset_count2-100
link = link.replace(
"offset=" + str(f_offset_count), "offset=" + str(f_offset_count2))
f_offset_count = f_offset_count2
else:
break
else:
break
else:
break
def process_chats(subscriber):
fool = subscriber["withUser"]
fool_id = str(fool["id"])
link_2 = f"https://onlyfans.com/api2/v2/chats/{fool_id}/messages?limit=100&offset=0&order=desc&app-token={app_token}"
xmessages(link_2)
if api_type == "Messages":
xmessages(link)
if api_type == "Mass Messages":
results = []
max_threads = multiprocessing.cpu_count()
offset_count = 0
offset_count2 = max_threads
while True:
def process_messages(link, session):
y = main_helper.json_request(session, link)
if y and "error" not in y:
return y
else:
return []
link_list = [link.replace(
"offset=0", "offset="+str(i*30)) for i in range(offset_count, offset_count2)]
link_list = pool.starmap(process_messages, product(
link_list, [sessions[0]]))
if all(not result for result in link_list):
break
link_list2 = list(chain(*link_list))
results.append(link_list2)
offset_count = offset_count2
offset_count2 = offset_count*2
unsorted_messages = list(chain(*results))
unsorted_messages.sort(key=lambda x: x["id"])
messages = unsorted_messages
def process_mass_messages(message, limit):
text = message["textCropped"].replace("&", "")
link_2 = "https://onlyfans.com/api2/v2/chats?limit="+limit+"&offset=0&filter=&order=activity&query=" + \
text+"&app-token="+app_token
y = main_helper.json_request(sessions[0], link_2)
if None == y or "error" in y:
return []
return y
limit = "10"
if len(messages) > 99:
limit = "2"
subscribers = pool.starmap(process_mass_messages, product(
messages, [limit]))
subscribers = filter(None, subscribers)
subscribers = [
item for sublist in subscribers for item in sublist["list"]]
seen = set()
subscribers = [x for x in subscribers if x["withUser"]
["id"] not in seen and not seen.add(x["withUser"]["id"])]
x = pool.starmap(process_chats, product(
subscribers))
if api_type == "Stories":
master_set.append(link)
if api_type == "Highlights":
r = main_helper.json_request(sessions[0], link)
if "error" in r:
return
for item in r:
link2 = f"https://onlyfans.com/api2/v2/stories/highlights/{item['id']}?app-token={app_token}"
master_set.append(link2)
master_set2 = main_helper.assign_session(master_set, sessions)
media_set = []
count = len(master_set2)
max_attempts = 100
for attempt in list(range(max_attempts)):
print("Scrape Attempt: "+str(attempt+1)+"/"+str(max_attempts))
media_set2 = pool.starmap(media_scraper, product(
master_set2, [sessions], [formatted_directories], [username], [api_type]))
media_set.extend(media_set2)
if count > 1:
faulty = [x for x in media_set2 if not x]
if not faulty:
print("Found: "+api_type)
break
else:
num = len(faulty)*100
print("Missing "+str(num)+" Posts... Retrying...")
master_set2 = main_helper.restore_missing_data(
master_set2, media_set2)
else:
print("No "+api_type+" Found.")
break
main_helper.delete_empty_directories(api_directory)
media_set = [x for x in media_set]
media_set = main_helper.format_media_set(media_set)
metadata_set = media_set
if export_metadata:
print
metadata_set = [x for x in metadata_set if x["valid"] or x["invalid"]]
for item in metadata_set:
if item["valid"] or item["invalid"]:
legacy_metadata = formatted_directories["legacy_metadata"]
if metadata_set:
os.makedirs(metadata_directory, exist_ok=True)
archive_directory = os.path.join(metadata_directory, api_type)
metadata_set_copy = copy.deepcopy(metadata_set)
metadata_set = main_helper.filter_metadata(metadata_set_copy)
main_helper.export_archive(
metadata_set, archive_directory, json_settings)
return [media_set, directory]
def prepare_scraper(api, site_name, item):
authed = api.auth
sessions = api.sessions
api_type = item["api_type"]
api_array = item["api_array"]
link = api_array["api_link"]
subscription = api_array["subscription"]
locations = api_array["media_types"]
username = api_array["username"]
directory = api_array["directory"]
api_count = api_array["post_count"]
master_set = []
media_set = []
metadata_set = []
pool = multiprocessing()
formatted_directories = main_helper.format_directories(
j_directory, site_name, username, locations, api_type)
model_directory = formatted_directories["model_directory"]
api_directory = formatted_directories["api_directory"]
metadata_directory = formatted_directories["metadata_directory"]
archive_directory = os.path.join(metadata_directory, api_type)
archive_path = archive_directory+".json"
imported = import_archive(archive_path)
legacy_metadata_directory = os.path.join(api_directory, "Metadata")
if api_type == "Profile":
profile_scraper(api, directory, username)
return
if api_type == "Stories":
master_set = subscription.get_stories()
highlights = subscription.get_highlights()
valid_highlights = []
for highlight in highlights:
highlight = subscription.get_highlights(
hightlight_id=highlight["id"])
valid_highlights.append(highlight)
master_set.extend(valid_highlights)
print
if api_type == "Posts":
master_set = subscription.get_posts()
if api_type == "Archived":
master_set = subscription.get_archived(api)
if api_type == "Messages":
unrefined_set = subscription.get_messages()
if "list" in unrefined_set:
unrefined_set = unrefined_set["list"]
if subscription.is_me:
mass_messages = authed["mass_messages"]
unrefined_set2 = process_mass_message(api,
subscription, metadata_directory, mass_messages)
unrefined_set += unrefined_set2
print
master_set = [unrefined_set]
master_set2 = master_set
parent_type = ""
if "Archived" == api_type:
unrefined_set = []
for master_set3 in master_set2:
parent_type = master_set3["type"]
results = master_set3["results"]
unrefined_result = pool.starmap(media_scraper, product(
results, [api], [formatted_directories], [username], [api_type], [parent_type]))
unrefined_set.append(unrefined_result)
unrefined_set = list(chain(*unrefined_set))
else:
unrefined_set = pool.starmap(media_scraper, product(
master_set2, [api], [formatted_directories], [username], [api_type], [parent_type]))
unrefined_set = [x for x in unrefined_set]
metadata_set = main_helper.format_media_set(unrefined_set)
if not metadata_set:
print("No "+api_type+" Found.")
delattr(subscription.scraped, api_type)
if metadata_set:
if export_metadata:
os.makedirs(metadata_directory, exist_ok=True)
old_metadata = metadata_fixer(archive_directory)
old_metadata_set = prepare_metadata(old_metadata).metadata
old_metadata_set2 = jsonpickle.encode(
old_metadata_set, unpicklable=False)
old_metadata_set2 = jsonpickle.decode(old_metadata_set2)
metadata_set = compare_metadata(metadata_set, old_metadata_set2)
metadata_set = prepare_metadata(metadata_set).metadata
metadata_set2 = jsonpickle.encode(metadata_set, unpicklable=False)
metadata_set2 = jsonpickle.decode(metadata_set2)
metadata_set2 = main_helper.filter_metadata(metadata_set2)
metadata_set2 = legacy_metadata_fixer(
legacy_metadata_directory, metadata_set2)
main_helper.export_archive(
metadata_set2, archive_directory, json_settings, legacy_directory=legacy_metadata_directory)
else:
metadata_set = prepare_metadata(metadata_set).metadata
subscription = api.get_subscription(username)
subscription.set_scraped(api_type, metadata_set)
return [subscription.scraped]