def get_total_comment_each_posts(soup, all_id_posts, all_tag_a_contain_total_comments_each_post): find_which_post_have_comments = [] all_total_comments_each_post = [] for x in all_tag_a_contain_total_comments_each_post: find_which_post_have_comments.append( get_text(x)) i = 0 for x in all_id_posts: html_post = find(soup, "div", "id", x) html_content_post = get_text(html_post) check_post_have_comments = html_content_post.find("Comment") if check_post_have_comments != -1: all_total_comments_each_post.append( find_which_post_have_comments[i]) i += 1 else: all_total_comments_each_post.append('0') return all_total_comments_each_post
def get_all_content_posts(driver, all_id_posts): HOME(driver) all_content_posts = [] for x in all_id_posts: while True: try: ele = driver.find_element_by_id(x) CLICK(driver, ele) soup = get_soup(driver) content_post = find( soup, "div", "class", "_5pbx userContent _3576") all_content_posts.append(get_text(content_post)) ESC(driver) break except Exception: pass END(driver) return all_content_posts
def get_text_from_html(tag_html): arr = [] for x in tag_html: arr.append(get_text(x)) return arr