Merge pull request #4 from ishanm0/feature-scraper

Modified scraper

.gitignore

@@ -0,0 +1,166 @@
+# API key files
+*google.json
+*openai.json
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

backend/app.py

@@ -1,4 +1,7 @@
 import io
+from threading import Thread
+import os
+import json
 
 from src.config import DATA_DIR_PATH
 from src.File.FileManager import create_unique_filename
@@ -11,17 +14,26 @@
     WebCrawler,
 )
 
+def upload_to_cloud(item):
+    filename = item["url"].replace("https://", "").replace("http://", "").replace("/", "-")+".json"
+    filename = os.path.join(DATA_DIR_PATH, filename)
+    upload_file(io.BytesIO(json.dumps(item, indent=4).encode("utf-8")), filename)
+    logger.info(f"Content from {item['url']} saved to {filename}")
+
 if __name__ == "__main__":
-    start_url = "https://www.ucsc.edu/"
+    start_url = "https://admissions.ucsc.edu/"
+    base_url = "ucsc.edu"
+
     max_depth = 10
 
     crawler = WebCrawler(SessionManager, LinkResolver, ContentExtractor)
-    crawled_data = crawler.crawl(start_url, max_depth)
+    crawled_data = crawler.crawl(start_url, base_url, max_depth)
+    num_crawled = 0
 
     for item in crawled_data:
-        filename = create_unique_filename(item["url"], DATA_DIR_PATH)
-        upload_file(io.BytesIO(item["text"].encode("utf-8")), filename)
-        logger.info(f"Content from {item['url']} saved to {filename}")
-
-    logger.info(f"Total pages crawled: {len(crawled_data)}")
+        thread = Thread(target=upload_to_cloud, args=(item,))
+        thread.start()
+        num_crawled += 1
+    
+    logger.info(f"Total pages crawled: {num_crawled}")
     logger.info("All crawled data has been saved to individual files.")

backend/src/Web/GoogleCloudStorage.py

@@ -38,7 +38,7 @@ def upload_file(file_stream, filename):
         return f"File '{filename}' uploaded successfully."
     except Exception as e:
         logger.error(f"Failed to upload file '{filename}': {str(e)}")
-        raise Exception(f"Failed to upload file: {str(e)}")
+        # raise Exception(f"Failed to upload file: {str(e)}")
 
 
 def download_file(filename):

backend/src/Web/WebCrawler.py

@@ -4,6 +4,9 @@
 from bs4 import BeautifulSoup
 from src.Logging.Logging import logger
 from src.Web.SSLAdapter import SSLAdapter
+import markdownify
+import re
+import tldextract
 
 
 class SessionManager:
@@ -30,16 +33,36 @@ class LinkResolver:
     """Handles URL resolution and filtering of links on a page."""
 
     @staticmethod
-    def resolve_links(base_url, soup, visited):
+    def resolve_links(url, soup, visited):
         links = []
         for link in soup.find_all("a", href=True):
             href = link["href"]
             if not href.startswith("http"):
-                href = requests.compat.urljoin(base_url, href)
+                href = requests.compat.urljoin(url, href)
             if href not in visited:
                 links.append(href)
         return links
 
+    @staticmethod
+    def resolve_links(url, base_url, soup, visited):
+        links = []
+        for link in soup.find_all("a", href=True):
+            href = link["href"]
+            if not href.startswith("http"):
+                href = requests.compat.urljoin(url, href)
+            if href not in visited and LinkResolver.same_domain(href, base_url) and not "#" in href:
+                links.append(href)
+        return links
+
+    @staticmethod
+    def same_domain(url, base_url):
+        sub_parts = tldextract.extract(url)
+        parent_parts = tldextract.extract(base_url)
+
+        # Compare the root domain and suffix
+        return (sub_parts.domain == parent_parts.domain and
+                sub_parts.suffix == parent_parts.suffix)
+
 
 class ContentExtractor:
     """Extracts and cleans text content from a given HTML page."""
@@ -55,7 +78,14 @@ def extract_main_text(soup):
             return main_content.get_text(separator="\n", strip=True)
         else:
             return "No <main> content found."
+
+    @staticmethod
+    def convert_to_md(soup):
+        html = soup.find("main") or soup.find("body") or soup
+        text = markdownify.markdownify(str(html), strip=["a", "img"])
+        text = re.sub(r"\n\n+", "\n", text).strip()
 
+        return text
 
 class WebCrawler:
     """Crawls a website up to a given depth and returns page content."""
@@ -70,10 +100,9 @@ def __init__(
         self.link_resolver = link_resolver
         self.content_extractor = content_extractor
 
-    def crawl(self, start_url, max_depth):
+    def crawl(self, start_url, base_url, max_depth):
         visited = set()
         queue = deque([(start_url, 0)])
-        data = []
 
         while queue:
             url, depth = queue.popleft()
@@ -88,13 +117,13 @@ def crawl(self, start_url, max_depth):
                 response.raise_for_status()
                 soup = BeautifulSoup(response.text, "html.parser")
 
-                text = self.content_extractor.extract_main_text(soup)
-                data.append({"url": url, "depth": depth, "text": text})
-                new_links = self.link_resolver.resolve_links(url, soup, visited)
+                text = self.content_extractor.convert_to_md(soup)
+                data =  {"url": url, "title": soup.find('title').text, "depth": depth, "text": text}
+                new_links = self.link_resolver.resolve_links(url, base_url, soup, visited)
                 for link in new_links:
                     queue.append((link, depth + 1))
+
+                yield data
 
             except Exception as e:
                 logger.error(f"Error crawling {url}: {str(e)}")
-
-        return data

backend/src/config.py

@@ -10,5 +10,6 @@
 
 DataFileName = f"{datetime.datetime.now().strftime('%Y-%m-%d_%H-%M-%S')}.data"
 DATA_FILE_PATH = f".data/{FolderYear}/{FolderDate}/{DataFileName}"
-DATA_DIR_PATH = f"/{FolderDate}"
+# DATA_DIR_PATH = f"{FolderDate}/"
+DATA_DIR_PATH = "data/"
 os.makedirs(os.path.dirname(DATA_DIR_PATH), exist_ok=True)