From 05b58465b0b5caec2629885c7041b1fce24e47aa Mon Sep 17 00:00:00 2001
From: janlukasschroeder <janlukasschroeder@protonmail.com>
Date: Mon, 14 Oct 2024 16:13:47 -0400
Subject: [PATCH] added PDF Generator API

---
 README.md           | 23 +++++++++++++++++++++++
 examples.py         | 19 +++++++++++++++++++
 sec_api/__init__.py |  1 +
 sec_api/index.py    | 36 ++++++++++++++++++++++++++++++++++--
 setup.py            |  2 +-
 5 files changed, 78 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 3282b2a..70b2ca8 100644
--- a/README.md
+++ b/README.md
@@ -9,6 +9,7 @@ It includes:
 - [SEC Filing Search and Full-Text Search API](#sec-edgar-filings-query-api)
 - [Real-Time Filing Stream API](#sec-edgar-filings-real-time-stream-api)
 - [Filing Download & PDF Render API](#filing-render--download-api)
+- [PDF Generator API](#pdf-generator-api)
 
 **Converter & Extractor APIs:**
 
@@ -175,6 +176,28 @@ with open("filename.pdf", "wb") as f:
 
 > See the documentation for more details: https://sec-api.io/docs/sec-filings-render-api
 
+## PDF Generator API
+
+SEC filings, including Forms 10-K, 10-Q, 8-K, and others, are typically published in HTML, XML, or text formats. The PDF Generator API enables the conversion of any SEC filing or exhibit into a PDF file, preserving all original formatting, tables, images, and other elements from the filing.
+
+```python
+from sec_api import PdfGeneratorApi
+
+pdfGeneratorApi = PdfGeneratorApi("YOUR_API_KEY")
+
+# Form 8-K exhibit URL
+edgar_file_url = "https://www.sec.gov/ix?doc=/Archives/edgar/data/1320695/000132069520000148/ths12-31x201910krecast.htm"
+# Form 10-K filing URL
+# edgar_file_url = "https://www.sec.gov/Archives/edgar/data/320193/000032019320000096/aapl-20200926.htm"
+
+pdf_file = pdfGeneratorApi.get_pdf(edgar_file_url)
+
+with open("filename.pdf", "wb") as f:
+    f.write(pdf_file)
+```
+
+> See the documentation for more details: https://sec-api.io/docs/sec-filings-render-api
+
 ## SEC EDGAR Filings Real-Time Stream API
 
 The Stream API provides a live stream (aka feed) of newly published filings on SEC EDGAR via WebSockets. A new filing is sent to your connected client as soon as it is published.
diff --git a/examples.py b/examples.py
index c3d6162..c3d564f 100644
--- a/examples.py
+++ b/examples.py
@@ -1,5 +1,6 @@
 from sec_api.index import (
     RenderApi,
+    PdfGeneratorApi,
     XbrlApi,
     ExtractorApi,
     MappingApi,
@@ -43,6 +44,24 @@
     f.write(binary_data)
 # """
 
+#
+# PDF Generator API
+#
+"""
+pdfGeneratorApi = PdfGeneratorApi("YOUR_API_KEY")
+
+# Form 8-K exhibit URL
+edgar_file_url = "https://www.sec.gov/ix?doc=/Archives/edgar/data/1320695/000132069520000148/ths12-31x201910krecast.htm"
+# Form 10-K filing URL
+# edgar_file_url = "https://www.sec.gov/Archives/edgar/data/320193/000032019320000096/aapl-20200926.htm"
+
+pdf_file = pdfGeneratorApi.get_pdf(edgar_file_url)
+
+with open("filename.pdf", "wb") as f:
+    f.write(pdf_file)
+# """
+
+
 #
 # XBRL-to-JSON API example
 #
diff --git a/sec_api/__init__.py b/sec_api/__init__.py
index 9529306..bb93a91 100644
--- a/sec_api/__init__.py
+++ b/sec_api/__init__.py
@@ -2,6 +2,7 @@
 from sec_api.index import QueryApi
 from sec_api.index import FullTextSearchApi
 from sec_api.index import RenderApi
+from sec_api.index import PdfGeneratorApi
 
 # Extractor & Converter APIs
 from sec_api.index import XbrlApi
diff --git a/sec_api/index.py b/sec_api/index.py
index 3638ed6..8084993 100644
--- a/sec_api/index.py
+++ b/sec_api/index.py
@@ -5,7 +5,8 @@
 
 query_api_endpoint = "https://api.sec-api.io"
 full_text_search_api_endpoint = "https://api.sec-api.io/full-text-search"
-render_api_endpoint = "https://archive.sec-api.io"
+filing_download_api_endpoint = "https://archive.sec-api.io"
+pdf_generator_api_endpoint = "https://api.sec-api.io/filing-reader"
 xbrl_api_endpoint = "https://api.sec-api.io/xbrl-to-json"
 extractor_api_endpoint = "https://api.sec-api.io/extractor"
 #
@@ -102,7 +103,7 @@ class RenderApi:
 
     def __init__(self, api_key, proxies=None):
         self.api_key = api_key
-        self.api_endpoint = render_api_endpoint
+        self.api_endpoint = filing_download_api_endpoint
         self.proxies = proxies if proxies else {}
 
     def get_filing(self, url, return_binary=False):
@@ -146,6 +147,37 @@ def get_file(self, url, return_binary=False):
             handle_api_error(response)
 
 
+class PdfGeneratorApi:
+    """
+    Base class for PDF Generator API
+    """
+
+    def __init__(self, api_key, proxies=None):
+        self.api_key = api_key
+        self.api_endpoint = pdf_generator_api_endpoint
+        self.proxies = proxies if proxies else {}
+
+    def get_pdf(self, url):
+        response = {}
+        file_url = re.sub(r"ix\?doc=/", "", url)
+        _url = (
+            self.api_endpoint + "?type=pdf&url=" + file_url + "&token=" + self.api_key
+        )
+
+        # use backoff strategy to handle "too many requests" error.
+        for x in range(3):
+            response = requests.get(_url, proxies=self.proxies)
+            if response.status_code == 200:
+                return response.content
+            elif response.status_code == 429:
+                # wait 500 * (x + 1) milliseconds and try again
+                time.sleep(0.5 * (x + 1))
+            else:
+                handle_api_error(response)
+        else:
+            handle_api_error(response)
+
+
 class XbrlApi:
     """
     Base class for XBRL-to-JSON API
diff --git a/setup.py b/setup.py
index 9a800be..fef8c1b 100644
--- a/setup.py
+++ b/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name="sec-api",
-    version="1.0.23",
+    version="1.0.24",
     author="SEC API",
     author_email="support@sec-api.io",
     description="SEC EDGAR Filings API",