BeautifulSoup 4 Python Web Scraping to txt file

Question

I am trying to write the data to a text file that I scraped using BeautifulSoup It prints the data in the console but not to the file

import requests
from bs4 import BeautifulSoup
 
base_url = 'https://www.aaabbbccc.com'
r = requests.get(base_url)
soup = BeautifulSoup(r.text)

outF = open("myOutFile.txt", "w", encoding='utf-8')
for story_heading in soup.find_all(class_="col-md-4"): 
    
    if story_heading.a: 
        print(story_heading.a.text.replace("\n", " ").strip())
        outF.write(str(story_heading))
        outF.write("\n")
 
    else: 
        print(story_heading.contents[0].strip())

outF.close()   

Answer 1

Use the following method:

with open("myOutFile.txt", "w", encoding='utf-8') as outF:

Example

import requests
from bs4 import BeautifulSoup
 
base_url = 'https://stackoverflow.com/questions/65815005/beautifulsoup-4-python-web-scraping-to-txt-file'
r = requests.get(base_url)
soup = BeautifulSoup(r.text)

with open("myOutFile.txt", "w", encoding='utf-8') as outF:
    for story_heading in soup.find_all(class_="col-md-4"): 

        if story_heading.a: 
            print(story_heading.a.get_text())
            outF.write(str(story_heading))
            outF.write("\n")

        else: 
            print(story_heading.contents[0].strip())

Answer 2

I would always use a+ method!

If the text file doesn't exist on your hard-drive, it'll create it and write to it. If the text file exists, it'll append your content to the end of it!

with open("myOutFile.txt", "a+") as f:

import requests
from bs4 import BeautifulSoup
 
base_url = 'https://www.aaabbbccc.com'
r = requests.get(base_url)
soup = BeautifulSoup(r.text)

with open("myOutFile.txt", "a+", encoding='utf-8') as f:
    for story_heading in soup.find_all(class_="col-md-4"): 

        if story_heading.a: 
            print(story_heading.a.get_text())
            f.write(str(story_heading)+"\n")
        else: 
            print(story_heading.contents[0].strip())

Answer 3

I also found another solution that I wanted to share with you

import requests
from bs4 import BeautifulSoup

def print_to_text(base_url):
    r = requests.get(base_url)
    soup = BeautifulSoup(r.text, 'html.parser')
    with open("myOutFile.txt", "w", encoding='utf-8') as textfile:
        for paragraph in soup.find_all(class_="col-md-4"):
            textfile.write(paragraph.text.replace("<span>",""))

if __name__ == "__main__":
    
    base_url = "https://www.aaabbb.com"

    print_to_text(base_url)