Python Scrape Forum for Title for each Post

I’m new to Web scraping and new to Python. I want to scrape for the title of each Posting at the Forum of the URL, so then a new Post is created with 1 of the Titles below i’d like to receive a Mail with that Link of the Post.

With searching for the div structItem-title i receive the 23 Posting that are on 1 Page. But when i want to print the Text of each Posting i only receive <class ‘str’> for the print(type(first_result.text)) and <class ‘bs4.element.Tag’> for print(type(first_result)) .

Title for search

    # Jeti_DS_16 = soup.find_all(text="Jeti DS 16")
    # Jeti_DS_16_v2 = soup.find_all(text="Jeti DS 16 2")
    # Jeti_DC_16 = soup.find_all(text="Jeti DC 16")
    # Jeti_DC_16_v2 = soup.find_all(text="Jeti DC 16 2")

Code

from requests import get
from bs4 import BeautifulSoup
import re
import smtplib
import time
import lxml


URL = 'https://www.rc-network.de/forums/biete-rc-elektronik-zubeh%C3%B6r.135/'

headers = {
    "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36'}


def checkForSearchItem():

    response = get(URL)
    # print(response.text[:500])

    # page = requests.get(URL, headers=headers)
    # page = requests.get(URL, headers=headers).text
    # page = requests.get(URL).text
    # page = requests.get(URL)

    soup = BeautifulSoup(response.content, "lxml")
    # soup = BeautifulSoup(page.content, "html.parser")
    # soup = BeautifulSoup(page.text, "html.parser")

    search_for_class = soup.find_all(
        'div', class_='structItem-title')
    # search_for_main = soup.find_all(
    #     'div', class_="structItemContainer-group js-threadList")
    # Jeti_DS_16 = soup.find_all(text="Jeti DS 16")
    # Jeti_DS_16_v2 = soup.find_all(text="Jeti DS 16 2")
    # Jeti_DC_16 = soup.find_all(text="Jeti DC 16")
    # Jeti_DC_16_v2 = soup.find_all(text="Jeti DC 16 2")

    # if(Jeti_DC_16, Jeti_DC_16_v2, Jeti_DS_16, Jeti_DS_16_v2):
    #     send_mail()

    # print('Die Nummer {0} {1} {2} {3} wurden gezogen'.format(
    #     Jeti_DC_16, Jeti_DC_16_v2, Jeti_DS_16, Jeti_DS_16_v2))

    print(type(search_for_class))
    print(len(search_for_class))

    first_result = search_for_class[0]
    # print(type(first_result.h3))
    # print(type(first_result.div.a.text))
    # print(type(first_result.a.text))
    # print(type(first_result.p.text))
    # print(type(first_result.name.text))
    # print(type(first_result.title))
    print(type(first_result))
    print(type(first_result.text))
    # print(soup.div)


# def send_mail():

#     server_ssl = smtplib.SMTP_SSL('smtp.gmail.com', 465)
#     server_ssl.ehlo()
#     # server.starttls()
#     # server.ehlo()

#     server_ssl.login('Secure@gmail.com', 'SecurePassword')

#     subject = 'Es gibt ein neuer Post im RC-Network auf deine gespeicherte Anfragen. Sieh in dir an{Link to Post}'
#     body = 'Sieh es dir an Link: https://www.rc-network.de/forums/biete-rc-elektronik-zubeh%C3%B6r.135/'

#     msg = f"Subject: {subject}nn{body}"
#     emails = ["Secure@gmx.de"]

#     server_ssl.sendmail(
#         'Secure@gmail.com',
#         emails,
#         msg
#     )
#     print('e-Mail wurde versendet!')

#     server_ssl.quit


while(True):
    checkForSearchItem()
    time.sleep(600)
    # time.sleep(86400)

Answer

When you want to print the text you dont need type().The type() function is just to see which type a variable has (int, str,…). Without type() the code works fine for me, printing the text. This means, on the print statements instead of this:

print(type(first_result.text))

Write this:

print(first_result.text)

I hope thats what you problem was and I could help you. When you need the URI of the post, you have to get the a Tag inside the post div and extract from this your URI, like this:

def checkForSearchItem():

    response = get(URL)

    soup = BeautifulSoup(response.content, "lxml")

    posts = soup.find_all('div', class_='structItem-title')

    for post in posts:
        a_tag = post.find_all('a')[0] # The a-tag inside the div
        link = a_tag.get('href') # The href inside the a-tag
        url = f'https://www.rc-network.de{link}' # The full URI because the 'link' looks like /threads/sensoren-von-graupner.11835933/
        print(post.text)
        print(url)

Advertisement

Answer