Blue element's href value is what i want to access from this HTML
I tried few ways to print the link but didn't work.
My code below:-
discover_page = BeautifulSoup(r.text, 'html.parser')
finding_accounts = discover_page.find_all("a", class_="author track")
print(len(finding_accounts))
finding_accounts = discover_page.find_all('a[class="author track"]')
print(len(finding_accounts))
accounts = discover_page.select('a', {'class': 'author track'})['href']
print(len(accounts))
Output:-
0
0
TypeError: 'dict' object is not callable
URL of the webpage is https://society6.com/discover but URL changes to https://society6.com/society?show=2 after logging into my account
What am i doing wrong here?
note:- I am using selenium chrome browser here. Answer given here works in my terminal but not when i run the file
My full code:-
from selenium import webdriver
import time
import requests
from bs4 import BeautifulSoup
import lxml
driver = webdriver.Chrome()
driver.get("https://society6.com/login?done=/")
username = driver.find_element_by_id('email')
username.send_keys("exp4money@gmail.com")
password = driver.find_element_by_id('password')
password.send_keys("sultan1997")
driver.find_element_by_name('login').click()
time.sleep(5)
driver.find_element_by_link_text('My Society').click()
driver.find_element_by_link_text('Discover').click()
time.sleep(5)
r = requests.get(driver.current_url)
r.raise_for_status()
'''discover_page = BeautifulSoup(r.html.raw_html, 'html.parser')
finding_accounts = discover_page.find_all("a", class_="author track")
print(len(finding_accounts))
finding_accounts = discover_page.find_all('a[class="author track"]')
print(len(finding_accounts))
links = []
for a in discover_page.find_all('a', class_ = 'author track'):
links.append(a['href'])
#links.append(a.get('href'))
print(links)'''
#discover_page.find_all('a')
links = []
for a in discover_page.find_all("a", attrs = {"class": "author track"}):
links.append(a['href'])
#links.append(a.get('href'))
print(links)
#soup.find_all("a", attrs = {"class": "author track"})'''
soup = BeautifulSoup(r.content, "lxml")
a_tags = soup.find_all("a", attrs={"class": "author track"})
for a in soup.find_all('a',{'class':'author track'}):
print('https://society6.com'+a['href'])
codes in documentation is the one I was using experimenting with
If you wish to find all links without trying it manually in Beautifulsoup. Then go for requests-html
Sample code to grab all links,
from requests_html import HTMLSession
from bs4 import BeautifulSoup
url = 'https://society6.com/discover'
session = HTMLSession(mock_browser=True)
r = session.get(url, headers={'User-Agent': 'Mozilla/5.0'})
print(r.html.links)
print(r.html.absolute_links)
soup = BeautifulSoup(r.html.raw_html, 'html.parser')
a_tags = soup.find_all("a", attrs={"class": "author track"})
for a_tag in a_tags:
print(a_tag['href'])
import requests
from bs4 import BeautifulSoup
data = requests.get('https://society6.com/discover')
soup_data = BeautifulSoup(data.content, "lxml")
for a in soup_data.find_all('a',{'class':'author track'}):
print('https://society6.com'+a['href'])
As per your question to print the href from the desired elements you can use only Selenium using the following solution:
Code Block:
from selenium import webdriver from selenium.webdriver.chrome.options import Options from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.common.by import By from selenium.webdriver.support import expected_conditions as EC options = Options() options.add_argument("start-maximized") options.add_argument("disable-infobars") options.add_argument("--disable-extensions") options.add_argument("--disable-gpu") options.add_argument("--no-sandbox") driver = webdriver.Chrome(chrome_options=options, executable_path=r'C:\WebDrivers\ChromeDriver\chromedriver_win32\chromedriver.exe') driver.get("https://society6.com/login?done=/") WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "input#email"))).send_keys("exp4money@gmail.com") driver.find_element_by_css_selector("input#password").send_keys("sultan1997") driver.find_element_by_css_selector("button[name='login']").click() WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "a#nav-user-my-society>span"))).click() WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.LINK_TEXT, "Discover"))).click() hrefs_elements = WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CSS_SELECTOR, "a.author.track"))) for element in hrefs_elements: print(element.get_attribute("href"))Console Output:
https://society6.com/pivivikstrm https://society6.com/cafelab https://society6.com/cafelab https://society6.com/colorandcolor https://society6.com/83oranges https://society6.com/aftrdrk https://society6.com/alaskanmommabear https://society6.com/thindesign https://society6.com/colorandcolor https://society6.com/aftrdrk https://society6.com/aljahorvat https://society6.com/bribuckley https://society6.com/hennkim https://society6.com/franciscomffonseca https://society6.com/83oranges https://society6.com/nadja1 https://society6.com/beeple https://society6.com/absentisdesigns https://society6.com/alexandratarasoff https://society6.com/artdekay880 https://society6.com/annaki https://society6.com/cafelab https://society6.com/bribuckley https://society6.com/bitart https://society6.com/draw4you https://society6.com/cafelab https://society6.com/beeple https://society6.com/burcukorkmazyurek https://society6.com/absentisdesigns https://society6.com/deanng https://society6.com/beautifulhomes https://society6.com/aftrdrk https://society6.com/printsproject https://society6.com/bluelela https://society6.com/anipani https://society6.com/ecmazur https://society6.com/batkei https://society6.com/menchulica https://society6.com/83oranges https://society6.com/7115
来源：https://stackoverflow.com/questions/52345850/how-to-print-the-href-attributes-using-beautifulsoup-while-automating-through-se