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 1 Packages Projects Releases Wiki Activity

fix: disallow mailto: (#861)

Browse Source
This commit is contained in:
PeriniM 2025-01-06 04:27:44 +01:00
parent 5be7c497cd
commit 8d9c909923
1 changed files with 31 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
scrapegraphai/nodes/fetch_node_level_k.py
View File

@ -160,20 +160,42 @@ class FetchNodeLevelK(BaseNode):
def get_full_links(self, base_url: str, links: list) -> list: def get_full_links(self, base_url: str, links: list) -> list:
""" """
Converts relative URLs to full URLs based on the base URL. Converts relative URLs to full URLs based on the base URL.
Filters out non-web links (mailto:, tel:, javascript:, etc.).
Args: Args:
base_url (str): The base URL for resolving relative links. base_url (str): The base URL for resolving relative links.
links (list): A list of links to convert. links (list): A list of links to convert.
Returns: Returns:
list: A list of full URLs. list: A list of valid full URLs.
""" """
# List of invalid URL schemes to filter out
invalid_schemes = {
'mailto:', 'tel:', 'fax:', 'sms:', 'callto:', 'wtai:', 'javascript:',
'data:', 'file:', 'ftp:', 'irc:', 'news:', 'nntp:', 'feed:', 'webcal:',
'skype:', 'im:', 'mtps:', 'spotify:', 'steam:', 'teamspeak:', 'udp:',
'unreal:', 'ut2004:', 'ventrilo:', 'view-source:', 'ws:', 'wss:'
}
full_links = [] full_links = []
for link in links: for link in links:
if self.only_inside_links and link.startswith("http"): # Skip if link starts with any invalid scheme
if any(link.lower().startswith(scheme) for scheme in invalid_schemes):
continue continue
full_link = link if link.startswith("http") else urljoin(base_url, link)
full_links.append(full_link) # Skip if it's an external link and only_inside_links is True
if self.only_inside_links and link.startswith(('http://', 'https://')):
continue
# Convert relative URLs to absolute URLs
try:
full_link = link if link.startswith(('http://', 'https://')) else urljoin(base_url, link)
# Ensure the final URL starts with http:// or https://
if full_link.startswith(('http://', 'https://')):
full_links.append(full_link)
except Exception as e:
self.logger.warning(f"Failed to process link {link}: {str(e)}")
return full_links return full_links
def obtain_content(self, documents: List, loader_kwargs) -> List: def obtain_content(self, documents: List, loader_kwargs) -> List:
@ -191,7 +213,11 @@ class FetchNodeLevelK(BaseNode):
for doc in documents: for doc in documents:
source = doc["source"] source = doc["source"]
if "document" not in doc: if "document" not in doc:
document = self.fetch_content(source, loader_kwargs) try:
document = self.fetch_content(source, loader_kwargs)
except Exception as e:
self.logger.warning(f"Failed to fetch content for {source}: {str(e)}")
continue
if not document or not document[0].page_content.strip(): if not document or not document[0].page_content.strip():
self.logger.warning(f"Failed to fetch content for {source}") self.logger.warning(f"Failed to fetch content for {source}")