├── uploaders ├── __init__.py ├── tiktok.py ├── facebook.py ├── instagram.py ├── youtube.py └── twitter.py ├── scraping_manager ├── __init__.py └── automate.py ├── spreadsheet_manager ├── __init__.py ├── google_ss.py └── xlsx.py ├── logo.png ├── requirements.txt ├── globals.py ├── .gitignore ├── LICENSE ├── download.py ├── config.py ├── __main__.py └── README.md /uploaders/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scraping_manager/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /spreadsheet_manager/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/darideveloper/video-post/HEAD/logo.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | selenium==3.141.0 2 | webdriver-manager==3.4.1 3 | requests==2.25.1 4 | moviepy==1.0.3 5 | gspread==4.0.1 6 | oauth2client==4.1.3 7 | -------------------------------------------------------------------------------- /globals.py: -------------------------------------------------------------------------------- 1 | global scraper 2 | global current_folder 3 | global videos_path 4 | global download_folder 5 | 6 | scraper = None 7 | current_folder = "" 8 | videos_path = "" 9 | download_folder = "" -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__ 2 | *__pycache__ 3 | *.json 4 | *temp.* 5 | temp.* 6 | *.log* 7 | *.log* 8 | *.zip 9 | *.png 10 | chrome_data 11 | downloads 12 | done 13 | videos.txt 14 | venv 15 | videos.xlsx 16 | *.mp4 -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2021 Dari Developer 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. -------------------------------------------------------------------------------- /uploaders/tiktok.py: -------------------------------------------------------------------------------- 1 | import time 2 | import globals 3 | 4 | def upload (file_path:str, title:str, description:str, tags:list): 5 | """ Upload video to tiktok """ 6 | 7 | print ("\tUploading video to Tiktok...") 8 | 9 | # Open page 10 | globals.scraper.set_page ("https://www.tiktok.com/upload?lang=en") 11 | time.sleep (5) 12 | 13 | # Add id to frame 14 | iframe_selector = "iframe" 15 | iframe = globals.scraper.get_elem (iframe_selector) 16 | globals.scraper.driver.execute_script("arguments[0].setAttribute('id', 'iframe');", iframe) 17 | time.sleep (2) 18 | globals.scraper.refresh_selenium () 19 | 20 | # Swicth to internal frame 21 | globals.scraper.switch_to_frame ("iframe") 22 | time.sleep (2) 23 | 24 | # Upload file 25 | selector_input = 'input[accept="video/*"]' 26 | globals.scraper.send_data (selector_input, file_path) 27 | time.sleep (10) 28 | 29 | # Video title and description 30 | selector_details = 'div[aria-autocomplete="list"][role="combobox"]' 31 | tag_text = "" 32 | for tag in tags: 33 | tag_text += f" #{tag}" 34 | text_formated = f" - {description} - {tag_text}" 35 | globals.scraper.send_data (selector_details, text_formated) 36 | time.sleep (1) 37 | 38 | # Post video 39 | selector_post = 'button.tiktok-btn-pc.tiktok-btn-pc-primary' 40 | globals.scraper.click_js (selector_post) 41 | time.sleep (15) -------------------------------------------------------------------------------- /uploaders/facebook.py: -------------------------------------------------------------------------------- 1 | import time 2 | import globals 3 | 4 | def upload (facebook_page, file_path:str, title:str, description:str, tags:list): 5 | """ Upload video to facebook page """ 6 | 7 | print ("\tUploading video to Facebook Page...") 8 | 9 | # Open page 10 | globals.scraper.set_page (facebook_page) 11 | time.sleep (5) 12 | 13 | # Start new post 14 | selector_new_post = 'div[aria-label="Create post"]' 15 | globals.scraper.click (selector_new_post) 16 | globals.scraper.refresh_selenium () 17 | time.sleep (2) 18 | 19 | 20 | # Select to upload photo or video 21 | selector_photo_video = '[aria-label="Photo/Video"][role="button"]' 22 | globals.scraper.click (selector_photo_video) 23 | time.sleep (2) 24 | 25 | # Upload file 26 | selector_input = 'input[accept="image/*,image/heif,image/heic,video/*,video/mp4,video/x-m4v,video/x-matroska,.mkv"]' 27 | globals.scraper.send_data (selector_input, file_path) 28 | time.sleep (10) 29 | globals.scraper.refresh_selenium () 30 | 31 | # Video title and description 32 | selector_details = '.k4urcfbm.l9j0dhe7.datstx6m.rq0escxv div[role="textbox"][contenteditable="true"]' 33 | tag_text = "" 34 | for tag in tags: 35 | tag_text += f"\n#{tag}" 36 | text_formated = f"{title}\n\n{description}\n{tag_text}" 37 | globals.scraper.click_js (selector_details) 38 | globals.scraper.send_data (selector_details, text_formated) 39 | time.sleep (1) 40 | globals.scraper.refresh_selenium () 41 | 42 | # Post video 43 | selector_post = 'input[type="submit"]' 44 | globals.scraper.click_js (selector_post) 45 | time.sleep (15) -------------------------------------------------------------------------------- /download.py: -------------------------------------------------------------------------------- 1 | import os 2 | import time 3 | import globals 4 | import requests 5 | 6 | def tiktok (tiktok_url:str, title:str): 7 | """Download video from tictok and save it in downloads folder 8 | 9 | Args: 10 | globals.scraper (object): web scraping instance 11 | tiktok_url (str): tiktok link 12 | """ 13 | 14 | print ("\tDownloading video...") 15 | 16 | # Open browser and go to snaptik 17 | time.sleep (5) 18 | globals.scraper.switch_to_tab (0) 19 | globals.scraper.set_page ("https://snaptik.app/en") 20 | 21 | # Paste link and start download 22 | selector_input = "#url" 23 | selector_submit = "#submiturl" 24 | globals.scraper.send_data(selector_input, tiktok_url) 25 | globals.scraper.click (selector_submit) 26 | 27 | # Wait for video load 28 | download_selector = 'a.abutton.is-success:nth-child(1)' 29 | 30 | try: 31 | globals.scraper.wait_load(download_selector, time_out=60) 32 | except: 33 | print ("Error to download, video omitted") 34 | 35 | # Close browser and end function 36 | globals.scraper.kill() 37 | return None 38 | 39 | # get file link and extension 40 | downlod_link = globals.scraper.get_attrib (download_selector, "href") 41 | separator = downlod_link.rfind (".") 42 | extension = downlod_link[separator+1:] 43 | 44 | # Download file 45 | file_path = os.path.join (os.path.dirname (__file__), "downloads", f"{title}.{extension}") 46 | mp4 (downlod_link, file_path) 47 | return file_path 48 | 49 | def mp4 (url:str, file_path:str): 50 | """ Download mp4 video from link """ 51 | 52 | res = requests.get (url) 53 | res.raise_for_status() 54 | with open (file_path, "wb") as file: 55 | for chunk in res.iter_content (chunk_size=8000): 56 | file.write (chunk) 57 | time.sleep (5) 58 | -------------------------------------------------------------------------------- /uploaders/instagram.py: -------------------------------------------------------------------------------- 1 | import time 2 | import globals 3 | from selenium.webdriver.common.keys import Keys 4 | 5 | def upload (file_path:str, title:str, description:str, tags:list): 6 | """ Upload video to instagram reels """ 7 | 8 | print ("\tUploading video to Instagram Reels...") 9 | 10 | # Open page 11 | instagram_url = "https://www.instagram.com/" 12 | globals.scraper.set_page (instagram_url) 13 | globals.scraper.set_page (instagram_url) 14 | globals.scraper.send_data ("body", Keys.CONTROL + Keys.SHIFT + "r") 15 | time.sleep (5) 16 | 17 | # Open reels 18 | selector_new = "nav.NXc7H.jLuN9 .J5g42 > .XrOey:nth-child(3)" 19 | globals.scraper.click (selector_new) 20 | globals.scraper.refresh_selenium () 21 | selector_reel = '.CreationPopup.CreationPopup_show > [data-id="reel"]' 22 | globals.scraper.click (selector_reel) 23 | globals.scraper.refresh_selenium () 24 | 25 | # Upload file 26 | selector_input = 'input[accept="video/mp4,video/quicktime"]' 27 | globals.scraper.send_data (selector_input, file_path) 28 | time.sleep (10) 29 | 30 | # Go to video details 31 | selector_continue = ".qF0y9.Igw0E.IwRSH.eGOV_._4EzTm.XfCBB.g6RW6" 32 | globals.scraper.click (selector_continue) 33 | time.sleep (2) 34 | globals.scraper.refresh_selenium () 35 | globals.scraper.click (selector_continue) 36 | time.sleep (2) 37 | globals.scraper.refresh_selenium () 38 | 39 | # Video title and description 40 | selector_details = 'textarea[aria-label="Write a caption..."]' 41 | tag_text = "" 42 | for tag in tags: 43 | tag_text += f"\n#{tag}" 44 | text_formated = f"{title}\n\n{description}\n{tag_text}" 45 | time.sleep (1) 46 | globals.scraper.send_data (selector_details, text_formated) 47 | 48 | # Share video 49 | selector_share = ".qF0y9.Igw0E.IwRSH.eGOV_._4EzTm.XfCBB.g6RW6" 50 | globals.scraper.click (selector_share) 51 | time.sleep (15) 52 | -------------------------------------------------------------------------------- /spreadsheet_manager/google_ss.py: -------------------------------------------------------------------------------- 1 | #! python3 2 | # Conect to google spreadsheets 3 | import os 4 | import gspread 5 | import time 6 | import sys 7 | from oauth2client.service_account import ServiceAccountCredentials 8 | 9 | class SS_manager (): 10 | """ Class to conect to google shets and upload data""" 11 | 12 | def __init__ (self, google_sheet_link, creds_path, sheet_name=None): 13 | """ Construtor of the class""" 14 | 15 | # Read credentials 16 | if not os.path.isfile (creds_path): 17 | raise FileNotFoundError ("The credential file path is not correct") 18 | 19 | scope = ['https://spreadsheets.google.com/feeds', 'https://www.googleapis.com/auth/drive'] 20 | creds = ServiceAccountCredentials.from_json_keyfile_name(creds_path, scope) 21 | client = gspread.authorize(creds) 22 | 23 | # Conect to google sheet 24 | sheet = client.open_by_url(google_sheet_link) 25 | 26 | # Set the sheet 1 as worksheet 27 | if sheet_name: 28 | self.worksheet = sheet.worksheet(sheet_name) 29 | else: 30 | self.worksheet = sheet.sheet1 31 | 32 | def write_cell (self, value, row=1, column=1): 33 | """ Write data in specific cell 34 | """ 35 | self.worksheet.update_cell(row, column, value) 36 | 37 | def write_data (self, data, row=1, column=1): 38 | """ Write list of data in the worksheet""" 39 | 40 | # check if data exist 41 | if not data: 42 | print ("THERE IS NO NEW INFORMATION TO WRITE IN THE FILE.") 43 | else: 44 | print ("Writing information on spreadsheet...") 45 | 46 | # Loop for each row of data 47 | for row_data in data: 48 | 49 | # Set the position of the next row. Omit the header 50 | row_index = data.index(row_data) + row 51 | 52 | for cell in row_data: 53 | column_index = row_data.index (cell) + column 54 | 55 | # Write data in gss 56 | print (cell, row_index, column_index) 57 | self.write_cell (cell, row_index, column_index) 58 | 59 | 60 | def get_data (self): 61 | """ Read all records of the sheet""" 62 | 63 | records = self.worksheet.get_all_records() 64 | return records -------------------------------------------------------------------------------- /uploaders/youtube.py: -------------------------------------------------------------------------------- 1 | import time 2 | import globals 3 | 4 | def upload (file_path:str, title:str, description:str, tags:list): 5 | """ Upload video to youtube shorts """ 6 | 7 | print ("\tUploading video to Youtube Shorts...") 8 | 9 | # Open page 10 | youtube_url = "https://studio.youtube.com/" 11 | globals.scraper.set_page (youtube_url) 12 | 13 | # Ignore browser warning 14 | selector_go_shorts = "body > div > div.buttons > a.button.text-button.black-secondary:only-child" 15 | try: 16 | globals.scraper.click (selector_go_shorts) 17 | except: 18 | pass 19 | globals.scraper.refresh_selenium() 20 | 21 | # Dimiss button 22 | selector_continue = "#dismiss-button" 23 | try: 24 | globals.scraper.click (selector_continue) 25 | except: 26 | pass 27 | globals.scraper.refresh_selenium() 28 | 29 | # Open upload 30 | selector_upload = "#upload-button" 31 | selector_upload_icon = "#upload-icon" 32 | try: 33 | globals.scraper.click_js (selector_upload) 34 | except: 35 | globals.scraper.click_js (selector_upload_icon) 36 | globals.scraper.refresh_selenium() 37 | 38 | # Upload file 39 | selector_input = 'input[type="file"]' 40 | globals.scraper.send_data (selector_input, file_path) 41 | globals.scraper.refresh_selenium() 42 | time.sleep (10) 43 | 44 | # Video title 45 | # selector_description = ".input-container.title #textbox" 46 | # globals.scraper.send_data (selector_description, title) 47 | 48 | # Video description 49 | selector_description = ".input-container.description #textbox" 50 | globals.scraper.send_data (selector_description, description) 51 | 52 | # No child content 53 | selector_no_child = "tp-yt-paper-radio-button:nth-child(2)" 54 | globals.scraper.click (selector_no_child) 55 | 56 | # Open more details 57 | selector_more = "#toggle-button" 58 | globals.scraper.click (selector_more) 59 | time.sleep (3) 60 | globals.scraper.refresh_selenium() 61 | 62 | # Tags 63 | selector_tags = "#tags-container #text-input" 64 | for tag in tags: 65 | globals.scraper.send_data (selector_tags, f"{tag}\n") 66 | 67 | # Next pages 68 | selector_next = "#next-button" 69 | globals.scraper.click (selector_next) 70 | globals.scraper.refresh_selenium() 71 | globals.scraper.click (selector_next) 72 | globals.scraper.refresh_selenium() 73 | globals.scraper.click (selector_next) 74 | globals.scraper.refresh_selenium() 75 | 76 | # Public type 77 | selector_public = 'tp-yt-paper-radio-button[name="PUBLIC"]' 78 | globals.scraper.click (selector_public) 79 | 80 | # Publish video 81 | selector_publish = "#done-button" 82 | globals.scraper.click (selector_publish) 83 | time.sleep (15) 84 | -------------------------------------------------------------------------------- /uploaders/twitter.py: -------------------------------------------------------------------------------- 1 | import time 2 | import download 3 | import globals 4 | from selenium.webdriver.common.keys import Keys 5 | 6 | def convert (file_path:str): 7 | """ Upload video to twitter """ 8 | 9 | print ("\tConverting video for twitter...") 10 | 11 | # Open converter page 12 | converter_url = "https://servicios-web.online-convert.com/es/convertir-para-twitter" 13 | globals.scraper.set_page (converter_url) 14 | 15 | # Upload video 16 | selector_input = "#fileUploadInput" 17 | globals.scraper.send_data (selector_input, file_path) 18 | 19 | # Start conversion 20 | selector_start = "button.btn.btn-lg.submit-btn.mb-0" 21 | last_url = globals.scraper.driver.current_url 22 | while True: 23 | globals.scraper.click (selector_start) 24 | time.sleep (2) 25 | current_url = globals.scraper.driver.current_url 26 | if current_url != last_url: 27 | break 28 | 29 | # Get download link 30 | while True: 31 | time.sleep (2) 32 | selector_download = 'a.btn.btn-large.btn-download[title="Descargar tu archivo"]' 33 | downlod_link = globals.scraper.get_attrib (selector_download, "href") 34 | if downlod_link and downlod_link != 'https://www.online-convert.com/es': 35 | time.sleep (10) 36 | downlod_link = globals.scraper.get_attrib (selector_download, "href") 37 | break 38 | else: 39 | continue 40 | 41 | # Download file 42 | file_converted = file_path.replace(".mp4", " for twitter.mp4") 43 | download.mp4 (downlod_link, file_converted) 44 | return file_converted 45 | 46 | 47 | def upload (file_path:str, title:str, description:str, tags:list): 48 | 49 | print ("\tUploading video to Twitter...") 50 | 51 | # Open page 52 | twitter_url = "https://twitter.com/home" 53 | globals.scraper.set_page (twitter_url) 54 | time.sleep (5) 55 | globals.scraper.refresh_selenium () 56 | 57 | # Upload file 58 | selector_input = 'input[accept="image/jpeg,image/png,image/webp,image/gif,video/mp4,video/quicktime,video/webm"]' 59 | globals.scraper.send_data (selector_input, file_path) 60 | time.sleep (10) 61 | 62 | # Video title and description 63 | selector_details = 'label[data-testid="tweetTextarea_0_label"] div[role="textbox"]' 64 | tag_text = "" 65 | for tag in tags: 66 | tag_text += f"\n#{tag}" 67 | text_formated = f"{title}\n\n{description}\n{tag_text}" 68 | globals.scraper.send_data (selector_details, text_formated) 69 | 70 | # Post tweet 71 | selector_share = 'div[data-testid="tweetButtonInline"]' 72 | globals.scraper.click_js (selector_share) 73 | 74 | # Wait to update video 75 | selector_placeholder = ".public-DraftEditorPlaceholder-inner" 76 | while True: 77 | time.sleep (2) 78 | place_holder = globals.scraper.get_text (selector_placeholder) 79 | if place_holder: 80 | break 81 | else: 82 | continue 83 | -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- 1 | import os 2 | import json 3 | 4 | current_file = os.path.basename(__file__) 5 | current_folder = os.path.dirname(__file__) 6 | default_config_path = os.path.join(current_folder, "config.json") 7 | 8 | class Config (): 9 | def __init__ (self, config_path=default_config_path, utf8=False): 10 | """Contructor of class 11 | 12 | Args: 13 | config_path (str/path, optional): Json file for process credentials. Defaults to config.json file. 14 | utf8 (bool, optional): Read or write data in utf8 format. Defaults to False. 15 | """ 16 | self.config_path=config_path 17 | self.utf8=utf8 18 | 19 | config_exist = os.path.isfile(self.config_path) 20 | if not config_exist: 21 | print (f"NOT FILE {self.config_path}") 22 | 23 | def get (self, credential=""): 24 | """ 25 | Get specific credential from config file 26 | """ 27 | 28 | # Read credentials file 29 | if self.utf8: 30 | config_file = open(self.config_path, "r", encoding='utf-8') 31 | else: 32 | config_file = open(self.config_path, "r") 33 | 34 | # Get specific credential 35 | try: 36 | config_data = json.loads(config_file.read()) 37 | return (config_data[credential]) 38 | except Exception as err: 39 | # print (err) 40 | return "" 41 | 42 | # Close file 43 | config_file.close() 44 | 45 | def get_all (self): 46 | """ 47 | return all crdentials from file 48 | """ 49 | 50 | # Read credentials file 51 | if self.utf8: 52 | config_file = open(self.config_path, "r", encoding='utf-8') 53 | else: 54 | config_file = open(self.config_path, "r") 55 | 56 | # Get specific credential 57 | try: 58 | config_data = json.loads(config_file.read()) 59 | return (config_data) 60 | except Exception as err: 61 | print (err) 62 | return "" 63 | 64 | # Close file 65 | config_file.close() 66 | 67 | def create_config (self, credentials, rewrite=False): 68 | """ 69 | Create a config file with default credentials 70 | """ 71 | 72 | if rewrite: 73 | open_mode = "w" 74 | else: 75 | open_mode = "a" 76 | 77 | with open (self.config_path, open_mode) as config_file: 78 | config_file.write(json.dumps(credentials)) 79 | 80 | 81 | def update (self, credential="", value=""): 82 | """ 83 | Update specific credential in config file 84 | """ 85 | 86 | with open (self.config_path, "r") as config_file: 87 | config_data = json.loads(config_file.read()) 88 | config_data[credential] = value 89 | 90 | with open (self.config_path, "w") as config_file: 91 | config_file.write(json.dumps(config_data)) 92 | 93 | def update_all (self, credentials, values): 94 | """ 95 | Update credentials 96 | """ 97 | 98 | for cred_config, cred_gui in credentials.items(): 99 | 100 | new_credential = values[cred_gui] 101 | self.update (cred_config, new_credential) -------------------------------------------------------------------------------- /spreadsheet_manager/xlsx.py: -------------------------------------------------------------------------------- 1 | import openpyxl 2 | from openpyxl.utils import get_column_letter 3 | from openpyxl.styles import Font 4 | 5 | class SS_manager (): 6 | """Manage local spread sheets 7 | """ 8 | 9 | def __init__(self, file_name): 10 | 11 | self.file_name = file_name 12 | self.wb = openpyxl.load_workbook(self.file_name) 13 | self.current_sheet = None 14 | 15 | def get_sheets (self): 16 | """ Return the list of sheets in the current document 17 | """ 18 | 19 | return self.wb.sheetnames 20 | 21 | 22 | def clean_workbook (self): 23 | """ Delete all sheets in current workbook 24 | """ 25 | 26 | for sheet in self.wb.sheetnames: 27 | sheet_obj = self.wb[sheet] 28 | self.wb.remove(sheet_obj) 29 | 30 | def create_get_sheet (self, sheet_name): 31 | """ Create a new sheet with specifici name, and set it as 32 | current sheet in class 33 | """ 34 | 35 | self.wb.create_sheet(sheet_name) 36 | self.set_sheet(sheet_name) 37 | 38 | def set_sheet (self, sheet_name): 39 | 40 | self.current_sheet = self.wb[sheet_name] 41 | 42 | def save (self): 43 | """Save current workbook 44 | """ 45 | 46 | self.wb.save(self.file_name) 47 | 48 | def write_cell (self, value="", row=1, column=1): 49 | """ Write data in specific cell 50 | """ 51 | 52 | self.current_sheet.cell (row, column).value = value 53 | 54 | def write_data (self, data=[], start_row=1, start_column=1): 55 | """ Write data list starting in specific cell 56 | """ 57 | 58 | current_row = start_row 59 | current_column = start_column 60 | 61 | for row in data: 62 | 63 | for cell_value in row: 64 | 65 | cell_obj = self.current_sheet.cell (current_row, current_column) 66 | cell_obj.value = cell_value 67 | 68 | current_column += 1 69 | 70 | current_column = start_column 71 | current_row += 1 72 | 73 | def auto_width (self): 74 | """ Set corect width to each coumn in the current sheet 75 | """ 76 | 77 | for col in self.current_sheet.columns: 78 | max_length = 0 79 | column = col[0].column_letter # Get the column name 80 | for cell in col: 81 | try: # Necessary to avoid error on empty cells 82 | if len(str(cell.value)) > max_length: 83 | max_length = len(str(cell.value)) 84 | except: 85 | pass 86 | adjusted_width = (max_length + 2) * 1.2 87 | self.current_sheet.column_dimensions[column].width = adjusted_width 88 | 89 | def format_range (self, start_cell=(1,1), end_cell=(1,1), italic=False, 90 | bold=False, font_size=8): 91 | 92 | # Create font style 93 | formated_font = Font(size=font_size, italic=italic, bold=bold) 94 | 95 | # Apply style 96 | current_row = start_cell[0] 97 | current_column = start_cell[1] 98 | 99 | for row in range(start_cell[0], end_cell[0] + 1): 100 | 101 | for cell_value in range(start_cell[1], end_cell[1] + 1): 102 | 103 | cell_obj = self.current_sheet.cell (current_row, current_column) 104 | cell_obj.font = formated_font 105 | 106 | current_column += 1 107 | 108 | current_column = 1 109 | current_row += 1 110 | 111 | def get_data (self): 112 | """ Get all data from the current page """ 113 | 114 | rows = self.current_sheet.max_row 115 | columns = self.current_sheet.max_column 116 | 117 | data = [] 118 | for row in range(1, rows + 1): 119 | 120 | row_data = [] 121 | for column in range(1, columns + 1): 122 | cell_data = self.current_sheet.cell (row, column).value 123 | row_data.append (cell_data) 124 | 125 | data.append (row_data) 126 | 127 | return data -------------------------------------------------------------------------------- /__main__.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import time 4 | import shutil 5 | import globals 6 | import datetime 7 | import download 8 | from uploaders import instagram, twitter, youtube, facebook, tiktok 9 | from config import Config 10 | from moviepy.editor import VideoFileClip 11 | from spreadsheet_manager.google_ss import SS_manager 12 | from scraping_manager.automate import Web_scraping 13 | 14 | # Get credentials 15 | credentials = Config() 16 | chrome_folder = credentials.get ("chrome_folder") 17 | facebook_page = credentials.get ("facebook_page") 18 | api_key = credentials.get ("api_key") 19 | sheet_url = credentials.get ("sheet_url") 20 | upload_instagram = credentials.get ("instagram") 21 | upload_facebook = credentials.get ("facebook") 22 | upload_twitter = credentials.get ("twitter") 23 | upload_youtube = credentials.get ("youtube") 24 | upload_tiktok = credentials.get ("tiktok") 25 | 26 | # Global variables 27 | globals.current_folder = os.path.dirname (__file__) 28 | globals.download_folder = os.path.join (globals.current_folder, "downloads") 29 | globals.chrome_folder = chrome_folder 30 | 31 | 32 | def start_scraper (): 33 | """ Start selenium with user settings and save as global variable 34 | """ 35 | 36 | 37 | # Start browser for install extensions 38 | globals.scraper = Web_scraping (headless=False, 39 | download_folder=globals.download_folder, 40 | chrome_folder=globals.chrome_folder) 41 | 42 | def get_video_duration (file_path:str): 43 | """Get the duration in seconds from specific video 44 | 45 | Args: 46 | file_path (str): path of the video 47 | 48 | Returns: 49 | float: duation in seconds 50 | """ 51 | clip = VideoFileClip(file_path) 52 | clip.close() 53 | return clip.duration 54 | 55 | def main (): 56 | """ 57 | Download videos from tiktok and post in: 58 | * facebook page 59 | * youtube shorts 60 | * instagram reels 61 | * twitter 62 | * tiktok 63 | """ 64 | 65 | # Get data from file 66 | print ("connecting with google sheet...") 67 | ss = SS_manager(sheet_url, api_key) 68 | videos_data = ss.get_data() 69 | 70 | # Main loop for each video 71 | output_data = [[]] 72 | for row in videos_data: 73 | 74 | # Get data from row 75 | date_time_text = row["date time"] 76 | video_url_name = row["url or name"] 77 | title = row["title"] 78 | description = row["description"] 79 | tags_text = row["tags"] 80 | processed = row["processed"] 81 | uploaded_instagram = row["uploaded instagram"] 82 | uploaded_facebook = row["uploaded facebook"] 83 | uploaded_twitter = row["uploaded twitter"] 84 | uploaded_youtube = row["uploaded youtube"] 85 | uploaded_tiktok = row["uploaded tiktok"] 86 | 87 | # Tags to list 88 | tags = tags_text.split(",") 89 | 90 | # Format date time 91 | date_time = datetime.datetime.strptime(date_time_text, "%m/%d/%Y %H:%M") 92 | 93 | # Validate video link 94 | if not video_url_name: 95 | break 96 | else: 97 | 98 | print (f"\nCurrent video: {title}") 99 | 100 | # Time validation 101 | now = datetime.datetime.now() 102 | if now > date_time: 103 | print (f"\tVideo skipped. The current time ({now}) is greater than the publication time ({date_time}).") 104 | output_data.append ([]) 105 | continue 106 | 107 | # Validate video processed 108 | if processed.lower().strip() == "yes": 109 | print ("\tVideo omitted, already processed") 110 | output_data.append ([]) 111 | continue 112 | else: 113 | 114 | start_scraper () 115 | 116 | # Wait time 117 | wait_time = date_time - now 118 | print (f"\tWaiting for the time: {date_time}...") 119 | time.sleep (wait_time.total_seconds()) 120 | 121 | # Default values for output uploaded in spreadsheet 122 | uploaded_instagram = "no" 123 | uploaded_facebook = "no" 124 | uploaded_twitter = "no" 125 | uploaded_youtube = "no" 126 | uploaded_tiktok = "no" 127 | processed = "yes" 128 | 129 | # Download video 130 | if "www.tiktok.com" in video_url_name: 131 | # Download tiktok video 132 | file_path = download.tiktok (video_url_name, title) 133 | else: 134 | # Validate video path 135 | file_path = os.path.join (globals.current_folder, "downloads", video_url_name) 136 | if not os.path.isfile (file_path): 137 | raise FileNotFoundError (file_path) 138 | 139 | duration = get_video_duration (file_path) 140 | 141 | # Validate duration for youtube and instagram 142 | if duration <= 60: 143 | # Upload video to youtube 144 | if upload_youtube: 145 | youtube.upload (file_path, title, description, tags) 146 | uploaded_youtube = "yes" 147 | 148 | # Upload video to instagram 149 | if upload_instagram: 150 | instagram.upload (file_path, title, description, tags) 151 | uploaded_instagram = "yes" 152 | 153 | # Upload video to tiktok 154 | if upload_tiktok: 155 | tiktok.upload (file_path, title, description, tags) 156 | uploaded_tiktok = "yes" 157 | else: 158 | print ("\tYoutube, Instagram and Tiktok: video skipped (60 sec it's max time for this pages)") 159 | 160 | # Validate duration for twitter 161 | if duration <= 140: 162 | if upload_twitter: 163 | # Convert video 164 | file_converted = twitter.convert (file_path) 165 | globals.scraper.kill () 166 | start_scraper () 167 | 168 | # Upload video to twitter 169 | twitter.upload (file_converted, title, description, tags) 170 | uploaded_twitter = "yes" 171 | 172 | # Move twitter file to done folder 173 | shutil.move (file_converted, file_converted.replace("downloads", "done")) 174 | 175 | else: 176 | print ("\tTwitter: video skipped (2:20 min it's max time for twitter)") 177 | 178 | # Post in faebook page without time validation 179 | if upload_facebook: 180 | facebook.upload (facebook_page, file_path, title, description, tags) 181 | uploaded_facebook = "yes" 182 | 183 | # End browser 184 | globals.scraper.kill() 185 | 186 | # Move file to done folder 187 | os.replace (file_path, file_path.replace("downloads", "done")) 188 | 189 | # Add row to output data 190 | output_data.append ([ 191 | date_time_text, 192 | video_url_name, 193 | title, 194 | description, 195 | tags_text, 196 | processed, 197 | uploaded_instagram, 198 | uploaded_facebook, 199 | uploaded_twitter, 200 | uploaded_youtube, 201 | uploaded_tiktok 202 | ]) 203 | 204 | # End browser 205 | try: 206 | globals.scraper.kill() 207 | except: 208 | pass 209 | 210 | # Update data in sheet 211 | ss.worksheet.update (output_data) 212 | print ("Done") 213 | 214 | 215 | if __name__ == "__main__": 216 | main() -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |
2 | MIT License 3 | 4 | Linkedin 5 | 6 | Telegram 7 | 8 | Github 9 | 10 | Fiverr 11 | 12 | Discord 13 | 14 | Gmail 15 |


Video Post 16 | 17 | # Video Post 18 | 19 | Download videos from tiktok and post in: 20 | * facebook page 21 | * youtube shorts 22 | * instagram reels 23 | * twitter 24 | * tiktok 25 | 26 | Project type: **client** 27 | 28 |

29 | Table of Contents 30 |
    31 |
  1. Build With
    2. 32 |
  2. Media
    3. 33 |
  3. Details
    4. 34 |
  4. Install
    5. 35 |
  5. Settings
    6. 36 |
  6. Run
37 |

38 | 39 | # Build with 40 | 41 |
Python Requests Selenium Google Sheets
42 | 43 | # Details 44 | 45 | ## Workflow 46 | 47 | 1. Checks if the current time and date match the publication date configured in the google sheet. 48 | 49 | 1. Validate the videos in *downloads* folder with the name or download it from tiktok. 50 | 51 | 2. Validate the duration of the video for each social network, and made the necessaries file conversions. 52 | 53 | Note: each social network have different limits of duration for the videos. 54 | If a video is longer than the page limits, it is automatically skipped. 55 | 56 | * **facebook:** 240 minutes 57 | * **youtube shorts:** 60 seconds 58 | * **instagram reels:** 60 seconds 59 | * **tiktok:** 60 seconds 60 | * **twitter:** 2:20 minutes 61 | 62 | Additional, for upload the videos to twitter, they require and extra conversion with the page: https://servicios-web.online-convert.com/es/convertir-para-twitter (This step is done automatically) 63 | 64 | 3. Post the video in each social network type the tilte, description and tags/keywords. 65 | 66 | 4. Move the video to **done** folder. 67 | 68 | After post all videos, the google sheet is updated. 69 | 70 | ## Warnings 71 | 72 | ### Youtube 73 | 74 | By default, youtube have a **limit of 15 uploads per day**. You can upload more videos with a manually verification. 75 | If you try to upload more videos without the verification, the program will raise an error. 76 | 77 | ### Instagram 78 | 79 | For upload reels to instagram, we use the extension **INSSIST**. 80 | At this time, the **extension have a bug** that allow us to **post reels without limits**, but when the developers fix it, **you will need to pay for the extension** to continue using the reels (at the moment, there are no other alternatives). 81 | 82 | ### Google chrome 83 | 84 | While the program is running, you will **not be able to use** your Google Chrome browser 85 | Also, make sure that when you start chrome, it **opens a new blank tab** (not the last open tabs), to avoid errors. 86 | 87 | ### Files 88 | 89 | The program **automatically replaces** the files in the "done" and "downloads" folders. Make sure you don't have any important videos with the same names as the spreadsheet, or you will lose it 90 | 91 | ### Updates 92 | 93 | This is a web automation project. 94 | Web automation **depends** entirely on the **structure of the page**, which means that **if any social network is updated** (for example, facebook) and changes the way videos are uploaded (a structural change (html) with or without changes layout (css)), **the project will need to be updated too**. 95 | 96 | # Install 97 | 98 | Install all modules from pip: 99 | 100 | ``` bash 101 | $ pip install -r requirements.txt 102 | ``` 103 | 104 | # Settings 105 | 106 | ## Programs 107 | 108 | To run the project, the following programs must be installed:: 109 | 110 | * [Google Chrome](https://www.google.com/intl/es/chrome) last version 111 | 112 | ## Generate Google API Key 113 | 114 | You can learn how to generate an API Key for google sheets, in this [tutorial](https://github.com/DariHernandez/tutorials/tree/master/generate%20google%20sheets%20api%20key) 115 | 116 | ## Create spreadsheet 117 | 118 | You need to create a spreadsheet in the same google account that generated your API Key. 119 | 120 | The name of the spreadsheet does not matter, but it is recommended to use "video post" or something similar, to easily identify it 121 | 122 | ### Columns 123 | 124 | The names of the columns are the following: 125 | 126 | *Note: all letters must be in lowercase and without spaces or extra characters* 127 | 128 | * date time 129 | * file or name 130 | * title 131 | * description 132 | * tags 133 | * processed 134 | * uploaded instagram 135 | * uploaded facebook 136 | * uploaded twitter 137 | * uploaded youtube 138 | * uploaded tiktok 139 | 140 | *Note: more detail about the google sheet in* **How to use > Google sheet** *section* 141 | 142 | ## Setup chrome 143 | 144 | This project does not require users and passwords to login, instead it will use the sessions that you already have opened in your browser. 145 | 146 | Before running the project, you need to do some extra steeps for prepare your google chrome. 147 | 148 | 1. Login to your instagram account. 149 | 2. Login to a facebook account how have access for post in the facebook page. 150 | 3. Login to yout twitter account. 151 | 4. Login to your youtube account. 152 | 5. Install the following extensions in chrome: [AdBlock](https://chrome.google.com/webstore/detail/adblock-%E2%80%94-best-ad-blocker/gighmmpiobklfepjocnamgkkbiglidom?hl=es-419) y [Insist](https://chrome.google.com/webstore/detail/inssist-web-client-for-in/bcocdbombenodlegijagbhdjbifpiijp?hl=en-US) 153 | 154 | ## Config file 155 | 156 | All **configurations** are saved in a **config.json file**, so **you can create and edit it manually** 157 | 158 | This is the content of the file (copy, paste, and replace with your datz): 159 | 160 | ```json 161 | { 162 | "chrome_folder": "C:\Users\{your user name}\AppData\Local\Google\Chrome\User Data", 163 | "facebook_page": "https://www.facebook.com/your_page_name/?ref=pages_you_manage", 164 | "api_key": "{project folder}\video post\sheets-340407-d8642222c103.json", 165 | "sheet_url": "https://docs.google.com/spreadsheets/d/1Eh1...iw0M/edit?usp=sharing", 166 | "instagram": false, 167 | "facebook": false, 168 | "twitter": true, 169 | "youtube": false, 170 | "tiktok": false 171 | 172 | } 173 | ``` 174 | 175 | ### chrome_folder 176 | The path of google chrome data. By default, in windows, there it in: **C:\Users\{your user name}\AppData\Local\Google\Chrome\User Data** 177 | 178 | ### api_key 179 | Path of your google api key in json format, generated in **Install > Generate Google API Key** section 180 | 181 | ### sheet_url 182 | Link of the google sheet with edit permissions. Here a [tutorial](https://github.com/DariHernandez/tutorials/tree/master/share%20google%20sheet%20with%20edit%20permissions) about how to generate the link 183 | 184 | ### facebook_page 185 | Link of your facebook page. 186 | 187 | ### instagram 188 | Post (true) or skip (false) all the videos for instagram 189 | 190 | ### facebook 191 | Post (true) or skip (false) all the videos for facebook 192 | 193 | ### twitter 194 | Post (true) or skip (false) all the videos for twitter 195 | 196 | ### youtube 197 | Post (true) or skip (false) all the videos for youtube 198 | 199 | ### tiktok 200 | Post (true) or skip (false) all the videos for youtube 201 | 202 | ## Google sheet 203 | 204 | Her the details about howe to use the columns in the google sheet: 205 | 206 | Column|description|sample 207 | |---|---|---| 208 | date time|Date and time in which the post should be published. Important: **dates must be in chronological order.** Format: mm/dd/yyyy h:m|02/05/2022 18:20 209 | url or name|tiktok video link or name of the file in the "downloads" folder (You can use any of the two and the program will detect it automatically)| https://www.tiktok.com/...8670874256902 or video1.mp4 210 | title|title of the video to post in all social networks| Dancing 211 | description|description / caption for add to the video| Hello, this is my first dancing video 212 | tags|keywords or hashtags, separated by commas| shorts,tiktok,dancing,funny 213 | processed|status of the video: processed by the program or not. By default, **no**| yes 214 | uploaded instagram|if the video is already processed, show if it have been posted in this social network. By default, **no**| no 215 | uploaded facebook|if the video is already processed, show if it have been posted in this social network. By default, **no**| yes 216 | uploaded twitter|if the video is already processed, show if it have been posted in this social network. By default, **no**| no 217 | uploaded youtube|if the video is already processed, show if it have been posted in this social network. By default, **no**| yes 218 | uploaded tiktok|if the video is already processed, show if it have been posted in this social network. By default, **no**| yes 219 | 220 | # Run 221 | 222 | After do the last steps, you can use the program running the **__ main__.py** or the project folder with your python 3.9 interpreter. 223 | 224 | Only, before of each running, be sure of: 225 | 226 | ## Before run 227 | 228 | ### Kill chrome processes 229 | 230 | **Kill/end** from task manager (windows) or htop (linux), **all google chrome processes**. 231 | 232 | Here a tutorial about how to [kill google chrome process in windows](https://github.com/DariHernandez/tutorials/tree/master/kill%20google%20chrome%20in%20windows) 233 | 234 | ### Close google sheet 235 | 236 | To ensure data integrity, do not edit or make changes to the spreadsheet while the program is running. 237 | 238 | -------------------------------------------------------------------------------- /scraping_manager/automate.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import time 4 | import logging 5 | import zipfile 6 | from selenium import webdriver 7 | from selenium.webdriver.common.keys import Keys 8 | from selenium.common.exceptions import TimeoutException 9 | import webdriver_manager 10 | from webdriver_manager.chrome import ChromeDriverManager 11 | from webdriver_manager.utils import ChromeType 12 | from selenium.webdriver.common.by import By 13 | from selenium.webdriver.support.ui import WebDriverWait 14 | from selenium.webdriver.support import expected_conditions as EC 15 | from selenium.webdriver.common.desired_capabilities import DesiredCapabilities 16 | 17 | current_file = os.path.basename(__file__) 18 | 19 | # Diable web driver manager logs 20 | logger_webdriver = logging.getLogger("webdriver_manager") 21 | logger_webdriver.setLevel(logging.ERROR) 22 | 23 | logger_selenium = logging.getLogger("selenium") 24 | logger_selenium.setLevel(logging.ERROR) 25 | 26 | class Web_scraping (): 27 | """ 28 | Class to manage and configure web browser 29 | """ 30 | 31 | def __init__ ( 32 | self, web_page="", headless=False, time_out=0, 33 | proxy_server="", proxy_port="", proxy_user="", proxy_pass="", 34 | chrome_folder="", user_agent=False, capabilities=False, 35 | download_folder="", extensions=[], incognito=False): 36 | """ 37 | Constructor of the class 38 | """ 39 | 40 | self.basetime = 1 41 | 42 | # variables of class 43 | self.__headless = headless 44 | self.__current_dir = os.path.dirname (__file__) 45 | self.__web_page = web_page 46 | self.__proxy_server = proxy_server 47 | self.__proxy_port = proxy_port 48 | self.__proxy_user = proxy_user 49 | self.__proxy_pass = proxy_pass 50 | self.__pluginfile = 'proxy_auth_plugin.zip' 51 | self.__chrome_folder = chrome_folder 52 | self.__user_agent = user_agent 53 | self.__capabilities = capabilities 54 | self.__download_folder = download_folder 55 | self.__extensions = extensions 56 | self.__incognito = incognito 57 | 58 | # Create and instance of the web browser 59 | self.__set_browser_instance() 60 | 61 | # Get current file name 62 | self.current_file = os.path.basename(__file__) 63 | 64 | # Set time out 65 | if time_out > 0: 66 | self.driver.set_page_load_timeout(30) 67 | 68 | def __set_browser_instance (self): 69 | """ 70 | Open and configure browser 71 | """ 72 | 73 | # Disable logs 74 | os.environ['WDM_LOG_LEVEL'] = '0' 75 | os.environ['WDM_PRINT_FIRST_LINE'] = 'False' 76 | 77 | # Configure browser 78 | options = webdriver.ChromeOptions() 79 | options.add_argument('--no-sandbox') 80 | options.add_argument('--start-maximized') 81 | options.add_argument('--output=/dev/null') 82 | options.add_argument('--log-level=3') 83 | options.add_argument("--disable-notifications") 84 | options.add_argument("disable-infobars") 85 | 86 | # Experimentals 87 | options.add_experimental_option('excludeSwitches', ['enable-logging', "enable-automation"]) 88 | options.add_experimental_option('useAutomationExtension', False) 89 | 90 | if self.__headless: 91 | options.add_argument("--window-size=1920,1080") 92 | options.add_argument("--headless") 93 | 94 | # Set proxy without autentication 95 | if (self.__proxy_server and self.__proxy_port 96 | and not self.__proxy_user and not self.__proxy_pass): 97 | 98 | proxy = f"{self.__proxy_server}:{self.__proxy_port}" 99 | options.add_argument(f"--proxy-server={proxy}") 100 | 101 | # Set proxy with autentification 102 | if (self.__proxy_server and self.__proxy_port 103 | and self.__proxy_user and self.__proxy_pass): 104 | 105 | self.__create_proxy_extesion() 106 | options.add_extension(self.__pluginfile) 107 | 108 | # Set chrome folder 109 | if self.__chrome_folder: 110 | options.add_argument(f"--user-data-dir={self.__chrome_folder}") 111 | 112 | # Set default user agent 113 | if self.__user_agent: 114 | options.add_argument('--user-agent=Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36') 115 | 116 | if self.__capabilities: 117 | capabilities = DesiredCapabilities.CHROME 118 | capabilities["goog:loggingPrefs"] = {"performance": "ALL"} 119 | else: 120 | capabilities = None 121 | 122 | if self.__download_folder: 123 | prefs = {"download.default_directory" : f"{self.__download_folder}", 124 | "download.prompt_for_download": True} 125 | options.add_experimental_option("prefs",prefs) 126 | 127 | if self.__extensions: 128 | for extension in self.__extensions: 129 | options.add_extension(extension) 130 | 131 | if self.__incognito: 132 | options.add_argument("--incognito") 133 | 134 | options.add_argument("--disable-blink-features=AutomationControlled") 135 | 136 | 137 | 138 | # Set configuration to and create instance 139 | chromedriver = ChromeDriverManager(chrome_type=ChromeType.GOOGLE, 140 | log_level='0', 141 | print_first_line=False).install() 142 | self.driver = webdriver.Chrome(chromedriver, 143 | options=options, 144 | service_log_path=None, 145 | desired_capabilities=capabilities) 146 | 147 | # Clean terminal 148 | # os.system('cls||clear') 149 | 150 | if self.__web_page: 151 | self.driver.get (self.__web_page) 152 | 153 | # Wait to load page 154 | # time.sleep (self.basetime*5) 155 | 156 | def __create_proxy_extesion (self): 157 | """Create a proxy chrome extension""" 158 | 159 | # plugin data 160 | manifest_json = """ 161 | { 162 | "version": "1.0.0", 163 | "manifest_version": 2, 164 | "name": "Chrome Proxy", 165 | "permissions": [ 166 | "proxy", 167 | "tabs", 168 | "unlimitedStorage", 169 | "storage", 170 | "", 171 | "webRequest", 172 | "webRequestBlocking" 173 | ], 174 | "background": { 175 | "scripts": ["background.js"] 176 | }, 177 | "minimum_chrome_version":"22.0.0" 178 | } 179 | """ 180 | 181 | background_js = """ 182 | var config = { 183 | mode: "fixed_servers", 184 | rules: { 185 | singleProxy: { 186 | scheme: "http", 187 | host: "%s", 188 | port: parseInt(%s) 189 | }, 190 | bypassList: ["localhost"] 191 | } 192 | }; 193 | 194 | chrome.proxy.settings.set({value: config, scope: "regular"}, function() {}); 195 | 196 | function callbackFn(details) { 197 | return { 198 | authCredentials: { 199 | username: "%s", 200 | password: "%s" 201 | } 202 | }; 203 | } 204 | 205 | chrome.webRequest.onAuthRequired.addListener( 206 | callbackFn, 207 | {urls: [""]}, 208 | ['blocking'] 209 | ); 210 | """ % (self.__proxy_server, self.__proxy_port, self.__proxy_user, self.__proxy_pass) 211 | 212 | # Compress file 213 | with zipfile.ZipFile(self.__pluginfile, 'w') as zp: 214 | zp.writestr("manifest.json", manifest_json) 215 | zp.writestr("background.js", background_js) 216 | 217 | def screenshot (self, base_name): 218 | """ 219 | Take a sreenshot of the current browser window 220 | """ 221 | 222 | if str(base_name).endswith(".png"): 223 | file_name = base_name 224 | else: 225 | file_name = f"{base_name}.png" 226 | 227 | self.driver.save_screenshot(file_name) 228 | 229 | def get_browser (self): 230 | """ 231 | Return the current instance of web browser 232 | """ 233 | 234 | return self.driver 235 | 236 | 237 | def end_browser (self): 238 | """ 239 | End current instance of web browser 240 | """ 241 | 242 | self.driver.close() 243 | 244 | 245 | def __reload_browser (self): 246 | """ 247 | Close the current instance of the web browser and reload in the same page 248 | """ 249 | 250 | self.end_browser() 251 | self.driver = self.get_browser() 252 | self.driver.get (self.__web_page) 253 | 254 | 255 | def send_data (self, selector, data): 256 | """ 257 | Send data to specific input fill 258 | """ 259 | 260 | elem = self.driver.find_element_by_css_selector (selector) 261 | elem.send_keys (data) 262 | 263 | 264 | def click (self, selector): 265 | """ 266 | Send click to specific element in the page 267 | """ 268 | 269 | elem = self.driver.find_element_by_css_selector (selector) 270 | elem.click() 271 | 272 | 273 | def wait_load (self, selector, time_out = 10, refresh_back_tab=-1): 274 | """ 275 | Wait to page load an element 276 | """ 277 | 278 | total_time = 0 279 | 280 | while True: 281 | if total_time < time_out: 282 | total_time += 1 283 | try: 284 | elem = self.driver.find_element_by_css_selector (selector) 285 | elem.text 286 | break 287 | except: 288 | 289 | # Wait time or refresh page 290 | if refresh_back_tab != -1: 291 | self.refresh_selenium(back_tab=refresh_back_tab) 292 | else: 293 | time.sleep (self.basetime) 294 | 295 | continue 296 | else: 297 | raise Exception ("Time out exeded. The element {} is not in the page".format (selector)) 298 | 299 | 300 | def wait_die (self, selector, time_out = 10): 301 | """ 302 | Wait to page vanish and element 303 | """ 304 | 305 | 306 | total_time = 0 307 | 308 | while True: 309 | if total_time < time_out: 310 | total_time += 1 311 | try: 312 | elem = self.driver.find_element_by_css_selector (selector) 313 | elem.text 314 | time.sleep(self.basetime) 315 | continue 316 | except: 317 | break 318 | else: 319 | raise Exception ("Time out exeded. The element {} is until in the page".format (selector)) 320 | 321 | 322 | def get_text (self, selector): 323 | """ 324 | Return text for specific element in the page 325 | """ 326 | 327 | try: 328 | elem = self.driver.find_element_by_css_selector (selector) 329 | return elem.text 330 | except Exception as err: 331 | # print (err) 332 | return None 333 | 334 | 335 | def get_texts (self, selector): 336 | """ 337 | Return a list of text for specific selector 338 | """ 339 | 340 | texts = [] 341 | 342 | elems = self.driver.find_elements_by_css_selector (selector) 343 | 344 | for elem in elems: 345 | try: 346 | texts.append(elem.text) 347 | except: 348 | continue 349 | 350 | return texts 351 | 352 | 353 | def get_attrib (self, selector, attrib_name): 354 | """ 355 | Return the class value from specific element in the page 356 | """ 357 | 358 | try: 359 | elem = self.driver.find_element_by_css_selector (selector) 360 | return elem.get_attribute(attrib_name) 361 | except: 362 | return None 363 | 364 | 365 | def get_attribs (self, selector, attrib_name, allow_duplicates=True, allow_empty=True): 366 | """ 367 | Return the attributes value from specific element in the page 368 | """ 369 | 370 | attributes = [] 371 | elems = self.driver.find_elements_by_css_selector (selector) 372 | 373 | for elem in elems: 374 | 375 | try: 376 | attribute = elem.get_attribute(attrib_name) 377 | 378 | # Skip duplicates in not duplicate mode 379 | if not allow_duplicates and attribute in attributes: 380 | continue 381 | 382 | # Skip empty results in not ampty mode 383 | if not allow_empty and attribute.strip() == "": 384 | continue 385 | 386 | attributes.append(attribute) 387 | 388 | except: 389 | continue 390 | 391 | return attributes 392 | 393 | def get_elem (self, selector): 394 | """ 395 | Return an specific element in the page 396 | """ 397 | 398 | elem = self.driver.find_element_by_css_selector (selector) 399 | return elem 400 | 401 | 402 | def get_elems (self, selector): 403 | """ 404 | Return a list of specific element in the page 405 | """ 406 | 407 | elems = self.driver.find_elements_by_css_selector (selector) 408 | return elems 409 | 410 | 411 | def set_page_js (self, web_page, new_tab=False): 412 | """Open page with js, in current or new tab 413 | """ 414 | 415 | self.__web_page = web_page 416 | 417 | if new_tab: 418 | script = f'window.open("{web_page}");' 419 | else: 420 | script = f'window.open("{web_page}").focus();' 421 | 422 | print (script) 423 | 424 | self.driver.execute_script(script) 425 | 426 | def set_page (self, web_page, time_out=0, break_time_out=False): 427 | """ 428 | Update the web page in browser 429 | """ 430 | 431 | try: 432 | 433 | self.__web_page = web_page 434 | 435 | # Save time out when is greader than 0 436 | if time_out > 0: 437 | self.driver.set_page_load_timeout(time_out) 438 | 439 | self.driver.get(self.__web_page) 440 | 441 | # Catch error in load page 442 | except TimeoutException: 443 | 444 | # Raise error 445 | if break_time_out: 446 | raise Exception(f"Time out to load page: {web_page}") 447 | 448 | # Ignore error 449 | else: 450 | self.driver.execute_script("window.stop();") 451 | 452 | 453 | 454 | 455 | def click_js (self, selector): 456 | """ 457 | Send click with js, for hiden elements 458 | """ 459 | 460 | elem = self.driver.find_element_by_css_selector (selector) 461 | self.driver.execute_script("arguments[0].click();", elem) 462 | 463 | 464 | def select_drop_dopwn (self, selector, item_index): 465 | """ 466 | Select specific elemet (with number) in a drop down elemet 467 | """ 468 | 469 | elem = self.driver.find_element_by_css_selector (selector) 470 | 471 | elem.click() 472 | for _ in range(0, item_index): 473 | time.sleep(0.1) 474 | elem.send_keys(Keys.DOWN) 475 | elem.send_keys(Keys.ENTER) 476 | 477 | 478 | def go_bottom (self): 479 | """ 480 | Go to the end of the page, sending keys 481 | """ 482 | 483 | elem = self.driver.find_element_by_css_selector ("body") 484 | elem.send_keys(Keys.CONTROL + Keys.END) 485 | 486 | 487 | def go_top (self): 488 | """ 489 | Go to the start of the page, sending keys 490 | """ 491 | 492 | elem = self.driver.find_element_by_css_selector ("body") 493 | elem.send_keys(Keys.CONTROL + Keys.UP) 494 | 495 | 496 | def go_down (self): 497 | """ 498 | advance to down, in the page, sending keys 499 | """ 500 | 501 | elem = self.driver.find_element_by_css_selector ("body") 502 | elem.send_keys(Keys.PAGE_DOWN) 503 | 504 | 505 | def go_up (self): 506 | """ 507 | Return to up, in page, sending keys 508 | """ 509 | 510 | elem = self.driver.find_element_by_css_selector ("body") 511 | elem.send_keys(Keys.PAGE_UP) 512 | 513 | 514 | def switch_to_main_frame (self): 515 | """ 516 | Switch to the main contecnt of the page 517 | """ 518 | 519 | self.driver.switch_to_default_content() 520 | 521 | 522 | def switch_to_frame (self, frame_id): 523 | """ 524 | Switch to iframe inside the main content 525 | """ 526 | 527 | self.driver.switch_to_frame(frame_id) 528 | 529 | 530 | def open_tab (self): 531 | """ 532 | Create new empty tab in browser 533 | """ 534 | 535 | self.driver.execute_script("window.open('');") 536 | 537 | 538 | def close_tab (self): 539 | """ 540 | Clase the current tab in the browser 541 | """ 542 | 543 | self.driver.close() 544 | 545 | 546 | def switch_to_tab (self, number): 547 | """ 548 | Switch to specific number of tab 549 | """ 550 | 551 | windows = self.driver.window_handles 552 | self.driver.switch_to.window(windows[number]) 553 | 554 | 555 | def refresh_selenium (self, time_units=1, back_tab=0): 556 | """ 557 | Refresh the selenium data, creating and closing a new tab 558 | """ 559 | 560 | # Open new tab and go to it 561 | self.open_tab() 562 | self.switch_to_tab(len(self.driver.window_handles)-1) 563 | 564 | # Wait time 565 | time.sleep(self.basetime * time_units) 566 | 567 | # Close new tab and return to specific tab 568 | self.close_tab() 569 | self.switch_to_tab(back_tab) 570 | 571 | # Wait time 572 | time.sleep(self.basetime * time_units) 573 | 574 | def save_page(self, file_html): 575 | """ Save current page in local file""" 576 | page_html = self.driver.page_source 577 | current_folder = os.path.dirname (__file__) 578 | page_file = open(os.path.join (current_folder, file_html), "w") 579 | page_file.write(page_html) 580 | page_file.close() 581 | 582 | def zoom (self, percentage=50): 583 | """ Custom page zoom with JS""" 584 | 585 | script = f"document.body.style.zoom='{percentage}%'" 586 | self.driver.execute_script (script) 587 | 588 | def kill (self): 589 | """ Detect and close all tabs """ 590 | tabs = self.driver.window_handles 591 | for _ in tabs: 592 | self.switch_to_tab(0) 593 | self.end_browser() 594 | 595 | def scroll (self, selector, scroll_x, scroll_y): 596 | """ Scroll X or Y in specific element of the page """ 597 | 598 | elem = self.get_elem(selector) 599 | self.driver.execute_script("arguments[0].scrollTo(arguments[1], arguments[2])", 600 | elem, 601 | scroll_x, 602 | scroll_y) 603 | --------------------------------------------------------------------------------