def timeline(self):
self.info['username'] = self.username
f = get_posts(self.username)
try:
for post in get_posts(self.username, pages=50):
if post['time'] and post['post_url']:
self.info['timestamps'][post['time'].strftime(
"%Y-%m-%d %H:%M:%S")] = post['post_url']
try:
self.info['words'].append(post['text'][:50])
if post['post_url']:
self.info['likes'][post['likes']] = post['post_url']
self.info['comments'][
post['comments']] = post['post_url']
except:
pass
except Exception as e:
pass
if not self.info['words']:
return False
return self.info
def get_data_item(params):
data = []
res = []
if params['type'] == 'fp':
res = get_posts(params['target'], pages=5)
else:
res = get_posts(group=params['target'], pages=5)
for d in res:
if d['image'] != None:
data.append({'id': d['post_id'], 'url': d['image']})
return data
async def steam(ctx):
## ##
await ctx.message.add_reaction('🎮')
channel = client.get_channel(769224265697329164)
reader = open("steampost.txt", "r")
list_string = reader.read()
reader.close()
writer = open("steampost.txt", "a")
post_list = list_string.split(" ")
try:
for post in get_posts('comusteambrasil', pages=2):
if str(post['post_id']) not in post_list:
embed = discord.Embed(title=str(post['time']),
description=post['text'],
color=0xff5555)
message = await channel.send(embed=embed)
await message.add_reaction('🥵')
await message.add_reaction('🥶')
writer.write(f" {post['post_id']}")
writer.close()
return
except Exception as err:
print(err)
def test_get_posts(self):
expected_post = {
'comments': 73,
'image': 'https://scontent.faqp2-3.fna.fbcdn.net/v/t1.0-9/fr/cp0/e15/q65/96724875_3065146506903115_4237164853036318720_o.jpg?_nc_cat=103&_nc_sid=8024bb&_nc_oc=AQmzJTxqWcBz-Q2u7AX_Aj_6bwv6V86hZS-v9BY-3w0h7jy9_LGi-LXss6UJuQn9xhk&_nc_ht=scontent.faqp2-3.fna&_nc_tp=14&oh=a057d46d536592575cce1605eac62dc4&oe=5EE011FB',
'images': [
'https://scontent.faqp2-3.fna.fbcdn.net/v/t1.0-9/fr/cp0/e15/q65/96724875_3065146506903115_4237164853036318720_o.jpg?_nc_cat=103&_nc_sid=8024bb&_nc_oc=AQmzJTxqWcBz-Q2u7AX_Aj_6bwv6V86hZS-v9BY-3w0h7jy9_LGi-LXss6UJuQn9xhk&_nc_ht=scontent.faqp2-3.fna&_nc_tp=14&oh=a057d46d536592575cce1605eac62dc4&oe=5EE011FB',
'https://scontent.faqp2-2.fna.fbcdn.net/v/t1.0-9/fr/cp0/e15/q65/96657922_3065146630236436_9052202957155598336_o.jpg?_nc_cat=101&_nc_sid=8024bb&_nc_ohc=HJe4yM4ZM-IAX_A4Gbb&_nc_ht=scontent.faqp2-2.fna&tp=14&oh=0f88fe17a844510b3ca40ecd53392657&oe=5FA220AD',
'https://scontent.faqp2-3.fna.fbcdn.net/v/t1.0-9/fr/cp0/e15/q65/96557798_3065146790236420_838564679184809984_o.jpg?_nc_cat=103&_nc_sid=8024bb&_nc_ohc=ZAWOX3v_GjwAX_nMJvh&_nc_ht=scontent.faqp2-3.fna&tp=14&oh=0351cb4b748dd6ce296dd02341f3f949&oe=5FA16534',
'https://scontent.faqp2-3.fna.fbcdn.net/v/t1.0-9/fr/cp0/e15/q65/96688092_3065146896903076_7861539131082407936_o.jpg?_nc_cat=108&_nc_sid=8024bb&_nc_ohc=G3b4bTeYIoEAX8IYjU4&_nc_ht=scontent.faqp2-3.fna&tp=14&oh=ae53e61554bfe97b85fe3dff884a4a2f&oe=5FA1DB01',
],
'video': None,
'video_thumbnail': None,
'likes': 1334,
'link': 'https://www.nintendo.com/wallpapers/',
'post_id': '3065154550235644',
'post_text': 'Check out these themed wallpapers and many more at the link '
'below for your personal use! We hope you enjoy them!\n\n'
'https://www.nintendo.com/wallpapers/',
'post_url': 'https://facebook.com/Nintendo/posts/3065154550235644',
'shared_text': '',
'shares': 0,
'text': 'Check out these themed wallpapers and many more at the link below '
'for your personal use! We hope you enjoy them!\n\n'
'https://www.nintendo.com/wallpapers/',
'time': datetime.datetime(2020, 5, 12, 20, 1, 18),
'user_id': '119240841493711',
'username': '******',
'video_id': None,
'is_live': False,
}
post = next(get_posts(account='Nintendo'))
assert post == expected_post
def test_get_posts(self):
expected_post = {
'comments':
73,
'image':
'https://scontent.faqp2-3.fna.fbcdn.net/v/t1.0-9/fr/cp0/e15/q65/96724875_3065146506903115_4237164853036318720_o.jpg?_nc_cat=103&_nc_sid=8024bb&_nc_oc=AQmzJTxqWcBz-Q2u7AX_Aj_6bwv6V86hZS-v9BY-3w0h7jy9_LGi-LXss6UJuQn9xhk&_nc_ht=scontent.faqp2-3.fna&_nc_tp=14&oh=a057d46d536592575cce1605eac62dc4&oe=5EE011FB',
'video':
None,
'likes':
1334,
'link':
'https://www.nintendo.com/wallpapers/',
'post_id':
'3065154550235644',
'post_text':
'Check out these themed wallpapers and many more at the link '
'below for your personal use! We hope you enjoy them!\n'
'https://www.nintendo.com/wallpapers/',
'post_url':
'https://m.facebook.com/story.php?story_fbid=3065154550235644&id=119240841493711',
'shared_text':
'',
'shares':
0,
'text':
'Check out these themed wallpapers and many more at the link below '
'for your personal use! We hope you enjoy them!\n'
'https://www.nintendo.com/wallpapers/',
'time':
datetime.datetime(2020, 5, 12, 20, 1, 18),
}
post = next(get_posts(account='Nintendo'))
assert post == expected_post
def check():
with NamedTemporaryFile(mode='w', delete=False) as tempfile:
with open('pages.csv', mode='r+') as csv_file, tempfile:
csv_reader = csv.DictReader(csv_file)
csv_writer = csv.DictWriter(tempfile, fields)
line_count = 0
csv_writer.writeheader()
for page in csv_reader:
temp = None
for post in get_posts(page['page_tag'], pages=1):
if post['time'] <= datetime.strptime(page['last_post_used'], date_format): # post already sent to channel
break
if post['image'] is not None:
bot.send_photo(chat_id, post['image'], (post['text'] if post['text'] else '')+ '\n[' + page['page_name'] + ']')
if (post['time'] > datetime.strptime(page['last_post_used'], date_format) and temp is None):
temp = post['time']
temp = post['time']
temp = post['time']
temp = post['time']
temp = post['time']
elif post['text'] is not None:
bot.send_message(chat_id, (post['text'] if post['text'] else '')+ '\n[' + page['page_name'] + ']')
if (post['time'] > datetime.strptime(page['last_post_used'], date_format) and temp is None):
temp = post['time']
if temp is not None:
page['last_post_used'] = temp
row = {'page_name': page['page_name'], 'page_tag': page['page_tag'], 'last_post_used': page['last_post_used']}
csv_writer.writerow(row)
def scrape_accounts(accounts):
posts = []
for account in accounts:
for post in get_posts(account, pages=5):
post['account'] = account
posts.append(post)
return posts
def command_add(update, context, *args):
user = User.objects.get(chat_id=args[0])
user_pages = eval(user.pages)
if len(args) == 7:
page = args[-1].lower()
else:
try:
page = update.message.text[5:].lower()
if page in user_pages:
update.message.reply_text(f"Page '{page}' Already Exist")
return
list(get_posts(page, pages=1))
except:
update.message.reply_text("Page Does Not Exist")
return
if page not in user_pages:
user_pages.append(page)
user.pages = user_pages
user.save()
else:
update.message.reply_text(f"Page '{page}' Already Exist")
return
try:
db_page = Page.objects.get(name=page)
subscribers = eval(db_page.subscribers)
subscribers.append(args[0])
db_page.save()
except Page.DoesNotExist:
Page.objects.create(name=page, last_update=0, subscribers=[args[0]])
update.message.reply_text(f"Page {page} Added Successfully!\n\nSee Your Pages With /list")
def get_data_from_group(self, keyword):
for group in self.groups:
for post in get_posts(group=group):
if post["text"]:
if keyword in post["text"]:
self.data = self.data + " " + post["text"]
return self.data
def extract_page_public_posts(page_name, count):
max_total_page = int(count / 2)
file_path = page_name + '_' + str(count) + '.json'
print('Saving to ' + file_path + '...')
data = []
_count = 0
try:
for post in get_posts(page_name,
pages=max_total_page,
extra_info=True,
timeout=15):
print(post)
if not (post['fail']):
del post['fail']
data.append(post)
_count = _count + 1
print(_count)
print('\n')
if (_count >= count):
break
except Exception as e:
print(e)
finally:
with open(file_path, "w", encoding='utf-8') as jsonfile:
json.dump(data, jsonfile, ensure_ascii=False)
def get_facebook_post(nombre_pagina, numero_paginas, id_campana, id_escucha,
id_red):
data_escucha = escucha.objects.get(id=id_escucha)
data_campana = campana_publicitaria.objects.get(id=id_campana)
data_red_social = red_social.objects.get(id=id_red)
for publicacion in get_posts(nombre_pagina, pages=numero_paginas):
if publicacion and publicacion["post_id"]:
data_red_escucha = data_red.objects.filter(
publicacion_id=publicacion["post_id"],
data_red_escucha=data_escucha,
data_red_campana=data_campana).values()
if not data_red_escucha:
if not publicacion["post_text"] or publicacion[
"post_text"] == None:
publicacion_texto = ""
else:
publicacion_texto = publicacion["post_text"]
new_publication = data_red(
publicacion_id=publicacion["post_id"],
publicacion_fecha=publicacion["time"],
publicacion_texto=publicacion_texto,
publicacion_likes=publicacion["likes"],
publicacion_comentarios=publicacion["comments"],
publicacion_compartidos=publicacion["shares"],
publicacion_user=publicacion["user_id"],
data_red_escucha=data_escucha,
data_red_campana=data_campana,
data_red_social=data_red_social)
new_publication.save()
logger.error('Task get facebook post completed succesfully')
def scraperpage(page, n, path=path):
path = path + str(page) + ".csv"
posts = get_posts(page, pages=n)
dataframe = pd.DataFrame(posts)
dataframe.to_csv(path, index=False)
return (path)
def routiney():
for post in get_posts('officialroutineofnepalbanda', pages=1):
# print('TIME: '+str(post['time'])+'\n')
# print(post['text']+'\n')
# print('Image: '+post['image']+'\n')
# print('Link to Post: '+post['post_url']+'\n\n')
time = str(post['time'])
f = open("r.txt", "r")
prev = f.read()
old = re.search(time, prev)
if old == None:
#if time!=prev:
if str(post['image']) != 'None':
data = {
'username': '******',
'avatar_url':
'https://pbs.twimg.com/profile_images/777188003445739521/t5GNGfAc_400x400.jpg',
'content': str(post['text']) + '\n' + post['image']
}
if str(post['image']) == 'None':
data = {
'username': '******',
'avatar_url':
'https://pbs.twimg.com/profile_images/777188003445739521/t5GNGfAc_400x400.jpg',
'content': str(post['text'])
}
response = requests.post(
'https://discord.com/api/webhooks/XXX/XXX-XXX', data=data)
last = str(post['time'])
f = open("r.txt", "a")
f.write(last)
f.close()
#sleep(120)
ok()
def scrap_facebook_post(n=100):
for client in clients:
posts = []
with open('../data/{}_fb_posts.json'.format(client), 'w') as json_file:
for post in get_posts(client, pages=n):
posts.append(post)
json.dump(posts, json_file, default=str)
def test_get_group_posts(self):
text = (
'Hola!, This group is aimed to create opportunities for South '
'American students in Computer Science and related fields.\n\n'
'Hope this will help us to know what we are doing in our work, '
'achievements to be recognized, increase fairness in our area, and '
'maybe conferences where we might meet.\n\n'
'Professors and professionals are also welcomed to share their '
'experiences and to collaborate among us and learn together.\n\n'
'Some short rules for a happy co-existence:\n'
'1. No business advertisement or spam.\n'
'2. Topics relevant to Computing, Computer Science, Software '
'Engineering, and Education.\n'
'3. Political and religious advertisement are not allowed.')
expected_post = {
'comments': 1,
'image': None,
'video': None,
'video_thumbnail': None,
'likes': 26,
'link': None,
'post_id': None,
'post_text': text,
'post_url': None,
'shared_text': '',
'shares': 0,
'text': text,
'time': datetime.datetime(2018, 4, 3, 20, 2, 0),
}
post = next(get_posts(group=117507531664134))
assert post == expected_post
def recent_posts(save=False):
#REPLACED WITH NEW FUNCTION pull_all_posts()
#Save arguement does not currently work - keep as FALSE
print("Getting most recent posts from the group...")
i=0
data = {}
data['postsData'] = []
for post in fs.get_posts(group='670932227050506/?sorting_setting=CHRONOLOGICAL'):
if post['post_id'] == None:
print(f' Post ID readings as none - cannot save post {i}')
else:
#print(post['post_id'])
data['postsData'].append(post)
i+=1
print(f"Retreived {i} posts from the group.")
if save is True:
print(f"Attempting to save retreived {i} posts from the group to file: {new_data_file}")
with open(new_data_file, 'w') as savefile:
try:
json.dump(data['postsData'], savefile)
print('Saved new posts successfully')
except:
print(f'Unable to save new posts to {new_data_file}')
print(type(data['postsData']))
return(data['postsData'])
def add_pages():
with open('pages.csv', 'a') as f:
csv_writer = csv.DictWriter(f, fields)
c = 'y'
while c != 'n':
row = {}
print("Give me a facebook page id:")
row['page_tag'] = input()
print("What name you want to associate to this page?:")
row['page_name'] = input()
print("Please wait while retrieving page info...")
posts = list(
get_posts(row['page_tag'], pages=3, cookies='cookies.txt'))
if len(posts) > 1:
if (int(posts[0]['post_id']) > int(posts[1]['post_id'])):
row['last_post_used'] = posts[0]['post_id']
else:
# first post is a pinned one
row['last_post_used'] = posts[1]['post_id']
elif len(posts) == 1:
row['last_post_used'] = posts[0]['post_id']
else:
row['last_post_used'] = 0
csv_writer.writerow(row)
print("...done.")
print("Do you want to add another page? [y/n]:")
while True:
c = input()
if c != 'y' and c != 'n':
print("Invalid input, please enter 'y' or 'n'")
else:
break
print('The bot is now configured, you can start it with ./scraper.py')
def getPosts(pages2):
posts = ' '
dataClean = []
for page in pages2:
for post in get_posts(page, pages=20):
if confimTime(post['time']):
if post['text'] != ' ':
print(post['time'])
try:
post = re.sub(r"<.*?>", ' ', post['text'])
post = re.sub(r'[0-9]', ' ', post)
post = re.sub(r' ', '', post)
post = re.sub(r'[a-zA-Z]', ' ', post)
post = re.sub(r'\n', ' ', post)
post = re.sub(r'[!.&é"'
'(-èê_çà)=$*ù^ù:;?#؟]', ' ', post)
posts = posts + post
except:
continue
text = re.findall(r'\w+', posts)
#remove stops words
for word in text:
if word not in stop_words:
dataClean.append(word)
r = pd.DataFrame({'data': dataClean})
r.to_csv("dataPosts.csv", index=False, encoding='utf-8-sig')
def scrape_page(self, page, pages=1):
self.page = page
posts = get_posts(page, pages=pages)
for e in posts:
# rate limit to avoid fb blocking
sleep(30)
self.download_post(e)
def get_facebook_posts():
name = request.args['name']
pageCount = int(request.args['pageCount'])
posts = list(get_posts(name, pages=pageCount))
return jsonify(posts)
def update_memes(fanpages: list, num_pages: int):
"""
Looks at FB fanpages and possibly adds new memes.
:param fanpages: List of fanpages.
:param num_pages: Number of pages of single fanpage to look.
"""
count = 0
new_count = 0
try:
memes = Meme.objects.all()
for fanpage in fanpages:
for post in get_posts(fanpage, pages=num_pages):
count += 1
post_url = post['post_url']
post_id = post['post_id']
image_url = post['image']
if post_url and post_id and image_url:
if not memes.filter(post_id=post_id).exists():
new_meme = Meme(post_id=post_id,
post_url=post_url,
image_url=image_url,
views=0,
valid=True)
new_count += 1
new_meme.save()
logging.info(f'Looked at {count} posts, added {new_count} new memes')
except Exception as e:
logging.exception("Exception occurred")
def check():
with open('fbpages.csv', mode='r+') as csv_file, NamedTemporaryFile(mode='w', delete=False) as tempfile:
csv_reader = csv.DictReader(csv_file)
csv_writer = csv.DictWriter(tempfile, fields)
line_count = 0
csv_writer.writeheader()
for page in csv_reader:
temp = None
posts = list(get_posts(page['fbpage_tag'], pages=2))
posts.sort(key = lambda x: x['time'])
for post in posts:
if post['time'] <= datetime.strptime(page['last_post_date'], date_format): # post already sent to channel
break
if post['image'] is not None:
bot.send_photo(chat_id, post['image'], (post['text'] if post['text'] else '')+ '\n[' + page['telegram_name'] + ']')
if (post['time'] > datetime.strptime(page['last_post_date'], date_format) and temp is None):
temp = post['time']
elif post['text'] is not None:
bot.send_message(chat_id, (post['text'] if post['text'] else '')+ '\n[' + page['telegram_name'] + ']')
if (post['time'] > datetime.strptime(page['last_post_date'], date_format) and temp is None):
temp = post['time']
if temp is not None:
page['last_post_date'] = temp
row = {'telegram_name': page['telegram_name'], 'fbpage_tag': page['fbpage_tag'], 'last_post_date': page['last_post_date']}
csv_writer.writerow(row)
shutil.move(tempfile.name, 'fbpages.csv')
threading.Timer(WAIT_SECONDS, check).start()
def get_page_posts():
json_posts = {}
# Run facebook-scraper
posts = get_posts(username, pages=3)
for i, post in enumerate(posts):
json_posts[i] = post
# Convert date time object to string
if json_posts[i]['time']:
json_posts[i]['time'] = str(json_posts[i]['time'])
# Store the posts data to JSON file
try:
with open(result_dir / (username + "-posts-fb-page.json"),
'w+',
encoding='utf-8') as jsonf:
jsonf.write(json.dumps(
json_posts,
indent=2,
))
except Exception as e:
logger.exception("Exception occurred")
# print(Fore.RED + type(e).__name__ + Fore.RESET + ": " + str(e))
print(
json.dumps({
"ERROR":
"Error occurred while storing Facebook page posts data, see logs for more details."
}))
def scrape(self):
# credentials = ("*****@*****.**", "TempPassword123")
# This lists will contain post related values.
translated_posts = []
user_id_list = []
# This lists will contain NLP related values.
bow_list = []
score_list = []
for post in get_posts(group=self.group, pages=10):
text = clean_post(post['text'])
user_id = str(post['user_id'])
if text != "" and user_id is not None and user_id != "None":
time.sleep(0.2)
translated_posts.append(self._translator.translate(text))
user_id_list.append(str(post['user_id']))
for translated_post in translated_posts:
bow_list.append(NPL_Engine.make_bag_of_words(translated_post))
score_list.append(
NPL_Engine.calculate_bow_relation_to_cluster(bow_list[-1]))
for score, facebook_id in zip(score_list, user_id_list):
if score > NPL_Engine.HAVER_THRESHOLD:
new_haver = Haver(facebook_id)
self._handler.add_haver_to_db(new_haver)
self._handler.commit()
return user_id_list
def text_handler(self, update, context):
"""
https://www.facebook.com/pagename/adss
https://m.facebook.com/pagename/adss
:param update:
:param context:
:return:
"""
self.start_time = time.time()
data = list(self.extract_message(update))
text = update.message.text
if 'facebook.com' in text:
try:
page = text.split('facebook.com')[1].split('/')[1]
list(get_posts(page, pages=1))
data.append(page)
Add.command_add(update, context, *tuple(data))
return
except:
update.message.reply_text("Invalid Link or Can't Add That Page.")
return
elif text == '.status':
update.message.reply_text(f"{BOT_ID}\n{(time.time() - self.start_time)//60} Minutes.")
return
update.message.reply_text("Unrecognized Text")
def setup():
print(
"This is the setup process for the bot, please be ready with the info required:"
)
print("- Telegram Bot Token can be found in your chat with @BotFather")
print("- The tag of the channel where the bot is admin")
print(
"- The ids of the facebook pages you are interested (can be found in the url https://www.facebook.com/"
+ '\033[1m' + "<page_id>" + '\033[0m' + ")")
print(
"- Cookies to connect to facebook, you can find instruction into the README.md file"
)
print("\nDo you want to proceed? [Y/n]")
proceed = input()
if proceed == 'n':
exit()
with open('config.py', 'w') as f:
print("Enter the Token:")
TOKEN = input()
print("Enter the chat/channel tag:")
chat_id = input()
if chat_id[0] == '@':
chat_id = chat_id[1:]
f.writelines([
"TOKEN = '" + TOKEN + "'" + '\n', "chat_id = '@" + chat_id + "'\n"
])
with open('pages.csv', 'w') as f:
csv_writer = csv.DictWriter(f, fields)
csv_writer.writeheader()
c = 'y'
while c != 'n':
row = {}
print("Give me a facebook page id:")
row['page_tag'] = input()
print("What name you want to associate to this page?:")
row['page_name'] = input()
print("Please wait while retrieving page info...")
posts = list(
get_posts(row['page_tag'], pages=3, cookies='cookies.txt'))
if len(posts) > 1:
if (int(posts[0]['post_id']) > int(posts[1]['post_id'])):
row['last_post_used'] = posts[0]['post_id']
else:
# first post is a pinned one
row['last_post_used'] = posts[1]['post_id']
elif len(posts) == 1:
row['last_post_used'] = posts[0]['post_id']
else:
row['last_post_used'] = 0
csv_writer.writerow(row)
print("...done.")
print("Do you want to add another page? [y/n]:")
while True:
c = input()
if c != 'y' and c != 'n':
print("Invalid input, please enter 'y' or 'n'")
else:
break
print('The bot is now configured, you can start it with ./scraper.py')
def getNewPosts(self):
"""Scrape the Facebook page for new posts, and filter out previously seen posts"""
CCTwitterBot.log('Retrieving new posts')
posts = fb.get_posts(self.pageName, pages=5)
posts = [p for p in posts if p['post_id'] not in self.state]
CCTwitterBot.log('Successfully retrieved {} new posts'.format(
len(posts)))
return posts
def getPost(page_name, key, enable_emoji=True):
for post in get_posts(page_name):
if key in post['text'][:]: # Looking for the clock emoji
if enable_emoji:
return post['text'][:]
else:
return remove_emoji(post['text'][:])
return None
def scrape(n):
for post in get_posts(n, pages=1):
fb_post_url = post['post_url']
# check against FB_list.csv
if df[Name]
print(fb_post_url)
sleep(10)
break
def scrap(i):
for posts in get_posts('alcheringaiitg', pages=i):
inst=socialMessage()
inst.message = posts['text']
inst.imglink = posts['image']
inst.save()
print('Scraping done!')
