added .get_file(url, return_binary=True) to RenderApi

Author: janlukasschroeder

README.md

@@ -163,6 +163,14 @@ url = "https://www.sec.gov/Archives/edgar/data/1662684/000110465921082303/tm2119
 filing = renderApi.get_filing(url)
 
 print(filing)
+
+# for non-text data, such as a PDF files or an images,
+# use get_file() and set `return_binary=True` to get the binary data
+pdf_file_url = "https://www.sec.gov/Archives/edgar/data/1798925/999999999724004095/filename1.pdf"
+binary_data = renderApi.get_file(pdf_file_url, return_binary=True)
+
+with open("filename.pdf", "wb") as f:
+    f.write(binary_data)
 ```
 
 > See the documentation for more details: https://sec-api.io/docs/sec-filings-render-api

examples.py

@@ -30,7 +30,17 @@
     url="https://www.sec.gov/ix?doc=/Archives/edgar/data/1320695/000132069520000148/ths12-31x201910krecast.htm"
 )
 
-print(filing_data)
+print(filing_data[:300])
+
+# for non-text data, such as a PDF files or an images,
+# use get_file() and set `return_binary=True` to get the binary data
+pdf_file_url = (
+    "https://www.sec.gov/Archives/edgar/data/1798925/999999999724004095/filename1.pdf"
+)
+binary_data = renderApi.get_file(pdf_file_url, return_binary=True)
+
+with open("filename.pdf", "wb") as f:
+    f.write(binary_data)
 # """
 
 #

sec_api/index.py

@@ -105,7 +105,7 @@ def __init__(self, api_key, proxies=None):
         self.api_endpoint = render_api_endpoint
         self.proxies = proxies if proxies else {}
 
-    def get_filing(self, url, as_pdf=False):
+    def get_filing(self, url, return_binary=False):
         response = {}
         # remove "ix?doc=/" from URL
         filename = re.sub(r"ix\?doc=/", "", url)
@@ -116,7 +116,27 @@ def get_filing(self, url, as_pdf=False):
         for x in range(3):
             response = requests.get(_url, proxies=self.proxies)
             if response.status_code == 200:
-                return response.text
+                return response.text if not return_binary else 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)
+
+    def get_file(self, url, return_binary=False):
+        response = {}
+        # remove "ix?doc=/" from URL
+        filename = re.sub(r"ix\?doc=/", "", url)
+        filename = re.sub(r"https://www.sec.gov/Archives/edgar/data", "", filename)
+        _url = self.api_endpoint + filename + "?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.text if not return_binary else response.content
             elif response.status_code == 429:
                 # wait 500 * (x + 1) milliseconds and try again
                 time.sleep(0.5 * (x + 1))

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name="sec-api",
-    version="1.0.22",
+    version="1.0.23",
     author="SEC API",
     author_email="support@sec-api.io",
     description="SEC EDGAR Filings API",