def download_pictures(user, password, thread_id, output_folder, msg_limit=100):
if not isdir(output_folder):
mkdir(output_folder)
client = Client(user, password)
if thread_id is None:
thread = client.fetchThreadList()[0]
msg_list = client.fetchThreadMessages(thread.uid, msg_limit)
else:
msg_list = client.fetchThreadMessages(thread_id=thread_id,
limit=msg_limit)
for msg in msg_list:
for att in msg.attachments:
att_valid = att.__class__.__name__ in "ImageAttachment, VideoAttachment".split(
", ")
if not att_valid:
continue
url = client.fetchImageUrl(att.uid)
data = http.request("GET", url=url, preload_content=False)
data = data.read()
try:
ext = att.original_extension
except AttributeError:
ext = re.match(".+\.([a-z0-9]{3,4})\?.+", url)
if ext is None:
ext = "unkown"
else:
ext = ext.groups()[0]
output_filename = join(output_folder, att.uid + "." + ext)
print("Downloading %s" % output_filename)
with open(output_filename, "wb") as f:
f.write(data)
def getImageURLs(client :Client):
#Gets a list of users with the given name and uses the first user in the list
users = client.searchForUsers('Testo Accounto')
user = users[0]
#Grabs the latest 10 messages in the thread with te given user and reverse the thread
messages = client.fetchThreadMessages(thread_id=user.uid, limit=10)
messages.reverse()
#Loops through all the messages and their attachments and tries to fetch the image's URL
#Also prints out the messages in the thread
for message in messages:
for attach in message.attachments:
print(client.fetchImageUrl(attach.uid))
print(message.text)
def main ():
if len(sys.argv) < 4:
print('Usage: python messenger_scraper.py facebook_username facebook_password conversation_id')
return False
facebook_username = sys.argv[1]
facebook_password = sys.argv[2]
conversation_id = sys.argv[3]
client = Client(facebook_username, facebook_password)
print('Attempting {}...'.format(conversation_id))
# what the f**k fbchat, where is function to retrieve all images?
# ehh I have to do everything by myself
lastMessageTimestamp = None
try:
os.mkdir(conversation_id)
except OSError:
print('Dir already exists!')
try:
while True:
messages = client.fetchThreadMessages(conversation_id, 100, lastMessageTimestamp)
lastMessageTimestamp = messages[len(messages)-1].timestamp
endOfMessages = False
for key,message in enumerate(messages):
if message.attachments:
for attachment in message.attachments:
try:
url = client.fetchImageUrl(attachment.uid)
except: continue
downloadImage(message.author, url, conversation_id, client)
if key == len(messages)-1 and key < 99:
endOfMessages = True
if endOfMessages == True:
break
except KeyboardInterrupt:
print('Downloading interrupted!')
def download_pictures(user, password, thread_id, output_folder):
downloaded = 0
if not isdir(output_folder):
mkdir(output_folder)
client = Client(user, password)
images = client.fetchThreadImages(thread_id)
for im in images:
if not type(im) == ImageAttachment:
continue
if (im.original_extension) == 'gif':
continue
img_filename = im.uid + ".jpg"
output_filename = join(output_folder, img_filename)
if (isFileExist(img_filename)):
print("File %s already downloaded" % img_filename)
continue
url = client.fetchImageUrl(im.uid)
data = http.request("GET", url=url, preload_content=False)
data = data.read()
downloaded += 1
print("Downloading %s" % output_filename)
with open(output_filename, "wb") as f:
f.write(data)
client.send(
Message(text="Synchronisation du cloud fini, nb photos telecharges: " +
str(downloaded)),
thread_id=client.uid,
thread_type=ThreadType.USER)
client.send(
Message(text="Synchronisation du cloud fini, nb photos telecharges: " +
str(downloaded)),
thread_id=thread_id,
thread_type=ThreadType.USER)
client.logout()
if len(message.attachments) > 0:
if (sender_id is None) or (sender_id == message.author):
for attachment in message.attachments:
if isinstance(attachment, ImageAttachment):
try:
attachment_ext = str.lower(
attachment.original_extension)
if attachment_ext not in extension_blacklist:
full_images.append({
'extension':
attachment_ext,
'timestamp':
message_datetime,
'full_url':
fb_client.fetchImageUrl(attachment.uid)
})
print('+', sep=' ', end='', flush=True)
else:
skip_count += 1
print('-', sep=' ', end='', flush=True)
total_count += 1
except FBchatException:
pass # ignore errors
last_message_date = message_datetime
# Download Full Images
if len(full_images) > 0:
images_count = len(full_images)
print("Message from other user/users")
dir_sub = "from_others"
if len(
message.attachments
) > 1 and args.onedir == False: #if enabled, create directory for more attachments in one message
dir = create_dir(dir_sub + '/' + msg_id)
else:
dir = "attachments/" + dir_sub
#-----create and chooose correct directory-----
#-----detect attachment type-----
if isinstance(current, ImageAttachment):
print("It's image")
extension = current.original_extension
url = client.fetchImageUrl(current.uid)
if isinstance(current, AudioAttachment):
print("It's audio")
filename = current.filename
extension = filename.split('.')[-1]
url = current.url
if isinstance(current, VideoAttachment):
print("It's video")
url = current.preview_url
if isinstance(current, FileAttachment):
print("It's a file")
url = current.url
print(url)
for message in messages:
message_datetime = convert_epoch_to_datetime(message.timestamp)
if len(message.attachments) > 0:
if (sender_id is None) or (sender_id == message.author):
for attachment in message.attachments:
if isinstance(attachment, ImageAttachment):
try:
attachment_ext = str.lower(attachment.original_extension)
if attachment_ext not in extension_blacklist:
full_images.append({
'extension': attachment_ext,
'timestamp': message_datetime,
'full_url': fb_client.fetchImageUrl(attachment.uid)
})
print('+', sep=' ', end='', flush=True)
else:
skip_count += 1
print('-', sep=' ', end='', flush=True)
total_count += 1
except FBchatException:
pass # ignore errors
last_message_date = message_datetime
# Download Full Images
if len(full_images) > 0:
images_count = len(full_images)
