Merge pull request #14 from pdftables/html-download

Add support for HTML download

Author: pwaller

pdftables_api/pdftables_api.py

@@ -20,6 +20,7 @@
 
 
 FORMAT_CSV = 'csv'
+FORMAT_HTML = 'html'
 FORMAT_XLSX_MULTIPLE = 'xlsx-multiple'
 FORMAT_XLSX_SINGLE = 'xlsx-single'
 FORMAT_XLSX = FORMAT_XLSX_MULTIPLE
@@ -29,17 +30,19 @@
 _DEFAULT_TIMEOUT = (10, 300)  # seconds (connect and read)
 _FORMATS_EXT = {
     FORMAT_CSV: '.csv',
+    FORMAT_HTML: '.html',
     FORMAT_XLSX: '.xlsx',
     FORMAT_XLSX_MULTIPLE: '.xlsx',
     FORMAT_XLSX_SINGLE: '.xlsx',
     FORMAT_XML: '.xml',
 }
 _EXT_FORMATS = {
     '.csv': FORMAT_CSV,
+    '.html': FORMAT_HTML,
     '.xlsx': FORMAT_XLSX,
     '.xml': FORMAT_XML,
 }
-_STRING_FORMATS = {FORMAT_CSV, FORMAT_XML}
+_STRING_FORMATS = {FORMAT_CSV, FORMAT_HTML, FORMAT_XML}
 
 class Client(object):
     def __init__(self, api_key, api_url=_API_URL, timeout=_DEFAULT_TIMEOUT):
@@ -87,6 +90,14 @@ def csv(self, pdf_path, csv_path=None):
         """
         return self.convert(pdf_path, csv_path, out_format=FORMAT_CSV)
 
+    def html(self, pdf_path, html_path=None):
+        """
+        Convenience method to convert HTML to CSV.
+
+        If html_path is None, returns the output as a string.
+        """
+        return self.convert(pdf_path, html_path, out_format=FORMAT_HTML)
+
     def convert(self, pdf_path, out_path=None, out_format=None, query_params=None, **requests_params):
         """
         Convert PDF given by `pdf_path` into `format` at `out_path`.

test/test_pdftables_api.py

@@ -39,6 +39,8 @@ def test_unmodified(self):
                          Client.ensure_format_ext('foo.xlsx', 'xlsx-multiple'))
         self.assertEqual(('foo.xml', 'xml'),
                          Client.ensure_format_ext('foo.xml', 'xml'))
+        self.assertEqual(('foo.html', 'html'),
+                         Client.ensure_format_ext('foo.html', 'html'))
 
     def test_missing_format(self):
         self.assertEqual(('foo.xlsx', 'xlsx-multiple'),