kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-07-20 13:47:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(web_fetch): support downloading and parsing remote document files (PDF, Word, Excel, PPT)

Browse Source
This commit is contained in:
zhayujie
2026-03-11 17:47:15 +08:00
parent 4fec55cc01
commit fa61744c6d
2 changed files with 14 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
agent/tools/web_fetch/web_fetch.py
View File

@@ -29,7 +29,7 @@ DEFAULT_HEADERS = {
# Supported document file extensions # Supported document file extensions
PDF_SUFFIXES: Set[str] = {".pdf"} PDF_SUFFIXES: Set[str] = {".pdf"}
WORD_SUFFIXES: Set[str] = {".doc", ".docx"} WORD_SUFFIXES: Set[str] = {".docx"}
TEXT_SUFFIXES: Set[str] = {".txt", ".md", ".markdown", ".rst", ".csv", ".tsv", ".log"} TEXT_SUFFIXES: Set[str] = {".txt", ".md", ".markdown", ".rst", ".csv", ".tsv", ".log"}
SPREADSHEET_SUFFIXES: Set[str] = {".xls", ".xlsx"} SPREADSHEET_SUFFIXES: Set[str] = {".xls", ".xlsx"}
PPT_SUFFIXES: Set[str] = {".ppt", ".pptx"} PPT_SUFFIXES: Set[str] = {".ppt", ".pptx"}
@@ -56,7 +56,7 @@ class WebFetch(BaseTool):
description: str = ( description: str = (
"Fetch content from a URL. For web pages, extracts readable text. " "Fetch content from a URL. For web pages, extracts readable text. "
"For document files (PDF, Word, TXT, Markdown, Excel, PPT), downloads and parses the file content. " "For document files (PDF, Word, TXT, Markdown, Excel, PPT), downloads and parses the file content. "
"Supported file types: .pdf, .doc, .docx, .txt, .md, .csv, .xls, .xlsx, .ppt, .pptx" "Supported file types: .pdf, .docx, .txt, .md, .csv, .xls, .xlsx, .ppt, .pptx"
) )
params: dict = { params: dict = {
@@ -226,29 +226,16 @@ class WebFetch(BaseTool):
return "\n\n".join(text_parts) return "\n\n".join(text_parts)
def _parse_word(self, file_path: str) -> str: def _parse_word(self, file_path: str) -> str:
"""Extract text from Word documents (.doc/.docx).""" """Extract text from Word documents (.docx)."""
suffix = os.path.splitext(file_path)[-1].lower()
if suffix == ".docx":
try:
from docx import Document
except ImportError:
raise ImportError(
"python-docx library is required for .docx parsing. Install with: pip install python-docx"
)
doc = Document(file_path)
paragraphs = [p.text for p in doc.paragraphs if p.text.strip()]
return "\n\n".join(paragraphs)
# .doc format - try textract or fallback
try: try:
import textract from docx import Document
text = textract.process(file_path).decode("utf-8")
return text
except ImportError: except ImportError:
raise ImportError( raise ImportError(
"textract library is required for .doc parsing. Install with: pip install textract" "python-docx library is required for .docx parsing. Install with: pip install python-docx"
) )
doc = Document(file_path)
paragraphs = [p.text for p in doc.paragraphs if p.text.strip()]
return "\n\n".join(paragraphs)
def _parse_text(self, file_path: str) -> str: def _parse_text(self, file_path: str) -> str:
"""Read plain text files (txt, md, csv, etc.).""" """Read plain text files (txt, md, csv, etc.)."""
@@ -344,7 +331,6 @@ class WebFetch(BaseTool):
"""Check if Content-Type indicates a binary/document response.""" """Check if Content-Type indicates a binary/document response."""
binary_types = [ binary_types = [
"application/pdf", "application/pdf",
"application/msword",
"application/vnd.openxmlformats", "application/vnd.openxmlformats",
"application/vnd.ms-excel", "application/vnd.ms-excel",
"application/vnd.ms-powerpoint", "application/vnd.ms-powerpoint",
@@ -358,7 +344,6 @@ class WebFetch(BaseTool):
ct_lower = content_type.lower() ct_lower = content_type.lower()
suffix_map = { suffix_map = {
"application/pdf": ".pdf", "application/pdf": ".pdf",
"application/msword": ".doc",
"application/vnd.openxmlformats-officedocument.wordprocessingml": ".docx", "application/vnd.openxmlformats-officedocument.wordprocessingml": ".docx",
"application/vnd.ms-excel": ".xls", "application/vnd.ms-excel": ".xls",
"application/vnd.openxmlformats-officedocument.spreadsheetml": ".xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml": ".xlsx",

6
requirements-optional.txt
View File

@@ -29,3 +29,9 @@ google-generativeai
# tencentcloud sdk # tencentcloud sdk
tencentcloud-sdk-python>=3.0.0 tencentcloud-sdk-python>=3.0.0
# file parsing (web_fetch document support)
pypdf
python-docx
openpyxl
python-pptx