| """ Get tweets from the profile page of a given USER """ | |
| import sys | |
| from selenium import webdriver | |
| from selenium.common.exceptions import TimeoutException | |
| from selenium.webdriver.common.by import By | |
| from selenium.webdriver.support.ui import WebDriverWait | |
| from selenium.webdriver.support import expected_conditions as EC | |
| # get twitter user from command-line | |
| if len(sys.argv) != 2: | |
| print('Usage: python ./script.py USER') | |
| sys.exit(2) | |
| user = sys.argv[1] | |
| # browse to webpage in firefox | |
| driver = webdriver.Firefox() | |
| driver.get('https://twitter.com/{}'.format(user)) | |
| try: | |
| # wait for a single article (i.e. tweet) to load async | |
| WebDriverWait(driver, 10).until( | |
| EC.presence_of_element_located((By.TAG_NAME, 'article'))) | |
| except TimeoutException as err: | |
| print('Error: {}'.format(err)) | |
| else: | |
| # get tweets on first page (if no exception thrown) | |
| articles = driver.find_elements_by_tag_name('article') | |
| for article in articles: | |
| spans = article.find_elements_by_tag_name('span') | |
| for span in spans: | |
| # ignore numbers of rt and fav | |
| if span.text.isdigit(): | |
| continue | |
| print(span.text, end=' ') | |
| print(end='\n') | |
| finally: | |
| # close opened browser tab | |
| driver.close() |
$ wget https://github.com/mozilla/geckodriver/releases/tag/v0.29.1
$ tar zxvf geckodriver-v0.29.1-linux64.tar.gz
$ vim ~/.bashrc
PATH="$PATH:/home/hakim/geckodriver/"$ pip3 install selenium