login to page with Selenium works - parsing with BS4 works - but not the combination of both

Question

getting some data from Wordpress-forums requires login and parsing - two parts. Both work very well as a standalone part. i can login with selenium - perfectly - and i can parse (scrape) the data with BS4. But when i combine the two parts then i run into session issues - that i cannot solve.

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup
import time
 
#--| Setup
options = Options()
#options.add_argument("--headless")
#options.add_argument("--window-size=1980,1020")
#options.add_argument('--disable-gpu')
browser = webdriver.Chrome(executable_path=r'C:\chrome\chromedriver.exe', options=options)
#--| Parse or automation
browser.get("https://login.wordpress.org/?locale=en_US")
time.sleep(2)
user_name = browser.find_element_by_css_selector('#user_login')
user_name.send_keys("the username ")
password = browser.find_element_by_css_selector('#user_pass')
password.send_keys("the pass")
time.sleep(5)
submit = browser.find_elements_by_css_selector('#wp-submit')[0]
submit.click()
 
# Example send page source to BeautifulSoup or selenium for parse
soup = BeautifulSoup(browser.page_source, 'lxml')
use_bs4 = soup.find('title')
print(use_bs4.text)
#print('*' * 25)
#use_sel = browser.find_elements_by_css_selector('div > div._1vC4OE')
#print(use_sel[0].text)

note - this works perfect. you can check it with the following combination:

login: pluginfan
pass: testpasswd123

see below the parser&scraper with bs4 - that works outstanding.

#!/usr/bin/env python3
 
import requests
from bs4 import BeautifulSoup as BS
 
session = requests.Session()
session.headers.update({'User-Agent': 'Mozilla/5.0'}) # this page needs header 'User-Agent`
 
url = 'https://wordpress.org/support/plugin/advanced-gutenberg/page/{}/'
 
for page in range(1, 3):
    print('\n--- PAGE:', page, '---\n')
 
    # read page with list of posts
    r = session.get(url.format(page))
 
    soup = BS(r.text, 'html.parser')
 
    all_uls = soup.find('li', class_="bbp-body").find_all('ul')
 
    for number, ul in enumerate(all_uls, 1):
 
        print('\n--- post:', number, '---\n')
 
        a = ul.find('a')
        if a:
            post_url = a['href']
            post_title = a.text
 
            print('text:', post_url)
            print('href:', post_title)
            print('---------')
 
            # read page with post content
            r = session.get(post_url)
 
            sub_soup = BS(r.text, 'html.parser')
 
            post_content = sub_soup.find(class_='bbp-topic-content').get_text(strip=True, separator='\n')
            print(post_content)

but the combination of both does not work: guess that i cannot create a new session with Requests,most work with the session that Selenium created i have some issues to run the parser with the login part

the stadalone parser gives back valid content - thats fine!

--- post: 1 ---
 
text: https://wordpress.org/support/topic/advanced-button-with-icon/
href: Advanced Button with Icon?
---------
is it not possible to create a button with a font awesome icon to left / right?
 
--- post: 2 ---
 
text: https://wordpress.org/support/topic/expand-collapse-block/
href: Expand / Collapse block?
---------
At the very bottom I have an expandable requirements.
Do you have a better block? I would like to use one of yours if poss.
The page I need help with:
 
--- post: 3 ---
 
text: https://wordpress.org/support/topic/login-form-not-formatting-correctly/
href: Login Form Not Formatting Correctly
---------
Getting some weird formatting with the email & password fields running on outside the form.
Tried on two different sites.
Thanks
 
..... [,,,,,] ....
 
--- post: 22 ---
 
text: https://wordpress.org/support/topic/settings-import-export-2/
href: Settings Import & Export
---------
Traceback (most recent call last):
  File "C:\Users\Kasper\Documents\_f_s_j\_mk_\_dev_\bs\____wp_forum_parser_without_login.py", line 43, in <module>
    print(post_content)
  File "C:\Program Files\Python37\lib\encodings\cp1252.py", line 19, in encode
    return codecs.charmap_encode(input,self.errors,encoding_table)[0]
UnicodeEncodeError: 'charmap' codec can't encode character '\U0001f642' in position 95: character maps to <undefined>
[Finished in 14.129s]

Any ideas?

Answer 1

EDIT: In both versions I added saving in CSV file.

---

If you have Selenium and requests then there are three posibility

• use Selenium to login and to get pages.
• use requests.Session to login and to get pages.
• use Selenium to login, get session information from Selenium and use them in requests

---

Using Selenium to login and to get pages is much simpler but it works slower then requests

It needs only to use

• browser.get(url) instead of r = session.get(post_url)
• BeautifulSoup(browser.page_source, ...) instead of BeautifulSoup(r.text, ...)

---

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup
import time
import csv

#--| Setup
options = Options()
#options.add_argument("--headless")
#options.add_argument("--window-size=1980,1020")
#options.add_argument('--disable-gpu')
browser = webdriver.Chrome(executable_path=r'C:\chrome\chromedriver.exe', options=options)
#browser = webdriver.Firefox()

# --- login ---

browser.get("https://login.wordpress.org/?locale=en_US")
time.sleep(2)

user_name = browser.find_element_by_css_selector('#user_login')
user_name.send_keys("my_login")
password = browser.find_element_by_css_selector('#user_pass')
password.send_keys("my_password")
#time.sleep(5)
submit = browser.find_elements_by_css_selector('#wp-submit')[0]
submit.click()
 
# Example send page source to BeautifulSoup or selenium for parse
soup = BeautifulSoup(browser.page_source, 'lxml')
use_bs4 = soup.find('title')
print(use_bs4.text)
#print('*' * 25)
#use_sel = browser.find_elements_by_css_selector('div > div._1vC4OE')
#print(use_sel[0].text)

# --- pages ---

data = []

url = 'https://wordpress.org/support/plugin/advanced-gutenberg/page/{}/'
 
for page in range(1, 3):
    print('\n--- PAGE:', page, '---\n')
 
    # read page with list of posts
    browser.get(url.format(page))
    soup = BeautifulSoup(browser.page_source, 'html.parser') # 'lxml'
 
    all_uls = soup.find('li', class_="bbp-body").find_all('ul')
 
    for number, ul in enumerate(all_uls, 1):
 
        print('\n--- post:', number, '---\n')
 
        a = ul.find('a')
        if a:
            post_url = a['href']
            post_title = a.text
 
            print('href:', post_url)
            print('text:', post_title)
            print('---------')
 
            # read page with post content
            browser.get(post_url)
            sub_soup = BeautifulSoup(browser.page_source, 'html.parser')
 
            post_content = sub_soup.find(class_='bbp-topic-content').get_text(strip=True, separator='\n')
            print(post_content)

            # keep on list as dictionary
            data.append({
                'href': post_url,
                'text': post_title,
                'content': post_content,
            })
            
# --- save ---

with open("wp-forum-conversations.csv", "w") as f:
    writer = csv.DictWriter(f, ["text", "href", "content"])
    writer.writeheader()
    writer.writerows(data)  # all rows at once

---

EDIT:

requests works much faster but it needs more work with DevTools in Firefox / Chrome to see all fields in form and what other values it sends to server. It needs also to see where it is redirect when logging is correct. BTW: don't forget to turn off JavaScript before using DevTools because requests doesn't run JavaScript and page may sends different values in form. (and it really sends different fields)

It needs full User-Agent to work correctly.

First I load login page and copy all values from <input> to send them with login and password

After login I check if it was redirected to different page - to confirm that it was logged correctly. You can also check if page display your name.

import requests
from bs4 import BeautifulSoup
import csv

s = requests.Session()
s.headers.update({
    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:80.0) Gecko/20100101 Firefox/80.0' # it needs full user-agent
})

# --- get page with login form ---

r = s.get("https://login.wordpress.org/?locale=en_US")
soup = BeautifulSoup(r.text, 'html.parser')

# get all fields in form

payload = {}

for field in soup.find_all('input'):
    name = field['name']
    value = field['value']
    payload[name] = value
    print(name, '=', value)

# --- login ---

payload['log'] = 'my_login'
payload['pwd'] = 'my_password'

r = s.post('https://login.wordpress.org/wp-login.php', data=payload)
print('redirected to:', r.url)

# --- check if logged in ---

# check if logged in - check if redirected to different page
if r.url.startswith('https://login.wordpress.org/wp-login.php'):
    print('Problem to login')
    exit()

# check if logged in - check displayed name
url = 'https://wordpress.org/support/plugin/advanced-gutenberg/page/1/'
r = s.get(url)

soup = BeautifulSoup(r.text, 'html.parser')
name = soup.find('span', {'class': 'display-name'})
if not name:
    print('Problem to login')
    exit()
else:    
    print('name:', name.text)
    
# --- pages ---

data = []

url = 'https://wordpress.org/support/plugin/advanced-gutenberg/page/{}/'
 
for page in range(1, 3):
    print('\n--- PAGE:', page, '---\n')
 
    # read page with list of posts
    r = s.get(url.format(page))
    soup = BeautifulSoup(r.text, 'html.parser') # 'lxml'
 
    all_uls = soup.find('li', class_="bbp-body").find_all('ul')
 
    for number, ul in enumerate(all_uls, 1):
 
        print('\n--- post:', number, '---\n')
 
        a = ul.find('a')
        if a:
            post_url = a['href']
            post_title = a.text
 
            print('href:', post_url)
            print('text:', post_title)
            print('---------')
 
            # read page with post content
            r = s.get(post_url)
            sub_soup = BeautifulSoup(r.text, 'html.parser')
 
            post_content = sub_soup.find(class_='bbp-topic-content').get_text(strip=True, separator='\n')
            print(post_content)

            # keep on list as dictionary
            data.append({
                'href': post_url,
                'text': post_title,
                'content': post_content,
            })
            
# --- save ---

with open("wp-forum-conversations.csv", "w") as f:
    writer = csv.DictWriter(f, ["text", "href", "content"])
    writer.writeheader()
    writer.writerows(data)  # all rows at once