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]