CodeCow/Scrapegraph-ai
1
0
Fork 0
mirror of https://github.com/VinciGit00/Scrapegraph-ai.git synced 2026-07-09 21:19:20 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

removed unused files
Some checks failed
CodeQL / Analyze (python) (push) Has been cancelled
Details
Release / Build (push) Has been cancelled
Details
Release / Release (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Marco Vinciguerra 2024-11-18 14:28:32 +01:00
parent 5a100fb2e8
commit a6269395a8
2 changed files with 0 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
extract_data.py
View File

@ -1,27 +0,0 @@
def extract_data(html: str) -> dict:
from bs4 import BeautifulSoup
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(html, 'html.parser')
# Initialize an empty list to hold project data
projects = []
# Find all project entries in the HTML
project_entries = soup.find_all('div', class_='grid-item')
# Iterate over each project entry to extract title and description
for entry in project_entries:
# Extract the title from the h4 element
title = entry.find('h4', class_='card-title').get_text(strip=True)
# Extract the description from the p element
description = entry.find('p', class_='card-text').get_text(strip=True)
# Append the extracted data as a dictionary to the projects list
projects.append({
'title': title,
'description': description
})
# Return the structured data as a dictionary matching the desired JSON schema
return {'projects': projects}

28
extracted_data.py
View File

@ -1,28 +0,0 @@
def extract_data(html: str) -> dict:
from bs4 import BeautifulSoup
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(html, 'html.parser')
# Initialize an empty list to hold project data
projects = []
# Find all project entries in the HTML
project_entries = soup.find_all('div', class_='grid-item')
# Iterate over each project entry to extract title and description
for entry in project_entries:
# Extract the title from the card-title class
title = entry.find('h4', class_='card-title').get_text(strip=True)
# Extract the description from the card-text class
description = entry.find('p', class_='card-text').get_text(strip=True)
# Append the extracted data as a dictionary to the projects list
projects.append({
'title': title,
'description': description
})
# Return the structured data as a dictionary matching the desired JSON schema
return {'projects': projects}