def main(argv=None): """登陆界面,先获取本地ip,然后登陆,并显示流量时长等信息 输入:空 输出:空 """ #检查输入 if argv is None: userid = default_userid passwd = default_passwd elif len(argv) == 1: userid = argv[0] passwd = default_passwd elif len(argv) == 2: userid = argv[0] passwd = argv[1] else: print("参数输入错误,请检查!") #post数据包 post_data['DDDDD'] = userid post_data['upass'] = passwd post_data['0MKKey'] = '' #检查是否连接成功,若成功,从返回参数中提取ip并显示ip地址 response = functions.requests_get(LOGIN_ADDR, user_timeout) title, script_text = functions.get_title(response) #若title为'欢迎登录北邮校园网络'说明连接成功,且为登录界面 if title == '欢迎登录北邮校园网络': functions.disp_local_ip(script_text) #连接成功后进行登录 response = functions.requests_post(LOGIN_ADDR, post_data) #获取title title, script_text = functions.get_title(response) if title == '登录成功窗': print("登陆成功") #显示信息 response = functions.requests_get(LOGIN_ADDR, user_timeout) title, script_text = functions.get_title(response) functions.display_info(script_text) elif title == '信息返回窗': functions.login_error(script_text) else: print("未知登陆错误,请检查并重试") #若返回title为上网注销窗,说明已经成功登录 elif title == "上网注销窗": print("已登陆成功") else: print("连接出现问题,请重试")
def search(): URL = "https://www.amazon.in/" driver = webdriver.Chrome('chromedriver') driver.implicitly_wait(10) driver.get(URL) #Using selenium to drive the browser search_button = driver.find_element_by_id("twotabsearchtextbox") search_term = str(input("What do you want?\n:")) search_button.send_keys(search_term) search_button.send_keys(Keys.ENTER) soup = bs4.BeautifulSoup(driver.page_source, "html5lib") links = soup.find_all('a', attrs={"class":"a-link-normal s-no-outline"})[:10] links_storage = [] for link in links: links_storage.append(link.get('href')) for link in links_storage: url = URL + link new_webpage = driver.get(url) new_soup = bs4.BeautifulSoup(driver.page_source, "html5lib") print() print("Name= ", get_title(new_soup)) print("Mrp= ", get_price_mrp(new_soup)) print("You pay= ", get_price_deal_price(new_soup)) print("Rating= ", get_rating(new_soup)) print("Reviews= ", get_review(new_soup)) print("Availability= ", get_availability(new_soup)) print("|") print("Link for the product= ", url) print("...................................next")
def main(): try: functions.read_file(sys.argv[1]) functions.get_app_num_pub_filing_date() if data.values[0] and data.values[1] != "": # to check if the page is a patent or not functions.get_title() functions.get_abstract() functions.get_name_of_applicant() functions.get_name_of_inventor() functions.get_int_class_priorty_doc_num() functions.get_int_app_pub_num() functions.print_data() else: print "Not a patent" except: print "Error in extracting"
def main(): """ 注销登陆,返回注销是否成功,并显示流量时长等信息 输入为空或用户名、密码 返回为空 """ response = functions.requests_get(LOGOUT_ADDR, user_timeout) title, script_text = functions.get_title(response) return_msg = re.search(r'Msg=(\d\d);', script_text).group(1) if title == "信息返回窗" and return_msg == '14': print("注销成功") functions.display_info(script_text) else: print("注销失败")
def inject_default_data(): data = { "locale": LOCALE, "locales": [LOCALE], "dark": True, "show_search": True, "request": request, "main_title": SITE_NAME, "title": get_title(request.path) } if is_authenticated(): data["email_hash"] = hashlib.md5(session["email"].encode()).hexdigest() data["name"] = session["name"] data["role"] = session["role"] return dict(data)
def get_info(html): """Функция для извлечения информации из html-кода. Вход : html-код Выход : список, состоящий из информации о заголовке, обложке, блок "Описание" блок основной информации, блок "Содержание", блок "Примечание". """ # Блок основной информации book_info = get_edition_notice(html) # Блок "Содержание" content = get_content(html) # Обложка книги cover = get_cover_image(html) # Заголовок title = get_title(html) # Блок "Описание" и "Примечание" opis, prim = get_book_info(html) return title, cover, book_info, opis, content, prim
URL = 'https://www.amazon.in/' driver = webdriver.Chrome("chromedriver") driver.implicitly_wait(10) driver.get(URL) search_button = driver.find_element_by_id("twotabsearchtextbox") search_term = str(input("What do you want?\n: ")) search_button.send_keys(search_term) search_button.send_keys(Keys.ENTER) #webpage = requests.get(URL, headers=HEADER) soup = bs4.BeautifulSoup(driver.page_source, 'html5lib') links = soup.find_all('a', attrs={'class':'a-link-normal s-no-outline'}) links_list = [] for link in links: links_list.append(link.get('href')) for link in links_list: new_webpage = driver.get(URL + link) new_soup = bs4.BeautifulSoup(driver.page_source, 'html5lib') #function calls print("Product Title=", get_title(new_soup)) print("Price=", get_price(new_soup)) print("Rating=", get_rating(new_soup)) print("User review=", get_review(new_soup)) print("Availability=", get_availability(new_soup)) print() print()
# ------------------ # ------------------------------------------------------------------------ # TEST 1 of 8: Compare Expected Title with HTML Title, OG Title, and # Twitter Title # ------------------------------------------------------------------------ print(" TEST 1 of 8: Title Check") # Build the expected title if station_slogan == None or station_slogan == "": expected_title = 'sanitized' % station_name else: expected_title = 'sanitized' % (station_name, station_slogan) expected_title = expected_title.upper() # Get the actual values from the web page html_title = functions.get_title(page_data) og_title = functions.get_meta_tag_content(page_data, "og:title", "") twitter_title = functions.get_meta_tag_content(page_data, "", "twitter:title") # Comparison time - all titles should match print(" Looking for : '%s'" % expected_title) print(" Title Tag Found : '%s'" % html_title) print(" OG Found : '%s'" % og_title) print(" Twitter Found : '%s'" % twitter_title) # Print Pass/Fail - Increment counters if actual/expected values don't match if expected_title == og_title and \ expected_title == twitter_title and \ expected_title == html_title: message = " TEST: %s\n" % PASSED
def page_title(): return jsonify(title=get_title(request.args.get("endpoint")))
# of truth" for these tests. # If station_slogan is None...or empty....the expected title changes if station_slogan == None or station_slogan == "": expected_title = 'sanitized' % station_name else: expected_title = 'sanitized' % (station_name, station_slogan) expected_title = expected_title.upper() # ------------------------------------------------------------------ # TEST: Compare Station API title with HTML <title>, og:title and # twitter:title. All 4 should match. # ------------------------------------------------------------------ print(" TEST: Title Comparison") # Function returns string in upper case html_title = functions.get_title(page_source) og_title = functions.get_meta_tag_content(page_source, "og:title") twitter_title = functions.get_meta_tag_content(page_source,"", "twitter:title") # Comparison time - all titles should match print(" Looking for : '%s'" % expected_title) print(" Title Tag Found: '%s'" % html_title) print(" OG Found : '%s'" % og_title) print(" Twitter Found : '%s'" % twitter_title) if expected_title == og_title and expected_title == twitter_title and \ expected_title == html_title: message = " TEST: %s\n" % PASSED else: message = " TEST: %s\n" % FAILED stations_failed += 1