Add extra_kwargs

camelot/handlers.py

@@ -125,7 +125,7 @@ class PDFHandler(object):
                 with open(fpath, 'wb') as f:
                     outfile.write(f)
 
-    def parse(self, flavor='lattice', suppress_stdout=False, **kwargs):
+    def parse(self, flavor='lattice', suppress_stdout=False, extra_kwargs={}, **kwargs):
         """Extracts tables by calling parser.get_tables on all single
         page PDFs.
 
@@ -136,6 +136,8 @@ class PDFHandler(object):
             Lattice is used by default.
         suppress_stdout : str (default: False)
             Suppress logs and warnings.
+        extra_kwargs : dict, optional (default: {})
+            A dict of pdfminer.layout.LAParams kwargs.
         kwargs : dict
             See camelot.read_pdf kwargs.
 
@@ -153,6 +155,7 @@ class PDFHandler(object):
                      for p in self.pages]
             parser = Lattice(**kwargs) if flavor == 'lattice' else Stream(**kwargs)
             for p in pages:
-                t = parser.extract_tables(p, suppress_stdout=suppress_stdout)
+                t = parser.extract_tables(p, suppress_stdout=suppress_stdout
+                                          extra_kwargs=extra_kwargs)
                 tables.extend(t)
         return TableList(tables)

camelot/io.py

@@ -6,7 +6,7 @@ from .utils import validate_input, remove_extra
 
 
 def read_pdf(filepath, pages='1', password=None, flavor='lattice',
-             suppress_stdout=False, **kwargs):
+             suppress_stdout=False, extra_kwargs={}, **kwargs):
     """Read PDF and return extracted tables.
 
     Note: kwargs annotated with ^ can only be used with flavor='stream'
@@ -26,6 +26,8 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
         Lattice is used by default.
     suppress_stdout : bool, optional (default: True)
         Print all logs and warnings.
+    extra_kwargs : dict, optional (default: {})
+        A dict of pdfminer.layout.LAParams kwargs.
     table_areas : list, optional (default: None)
         List of table area strings of the form x1,y1,x2,y2
         where (x1, y1) -> left-top and (x2, y2) -> right-bottom
@@ -98,5 +100,6 @@ def read_pdf(filepath, pages='1', password=None, flavor='lattice',
         validate_input(kwargs, flavor=flavor)
         p = PDFHandler(filepath, pages=pages, password=password)
         kwargs = remove_extra(kwargs, flavor=flavor)
-        tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout, **kwargs)
+        tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout,
+                         extra_kwargs=extra_kwargs, **kwargs)
         return tables

camelot/parsers/base.py

@@ -8,13 +8,10 @@ from ..utils import get_page_layout, get_text_objects
 class BaseParser(object):
     """Defines a base parser.
     """
-    def _generate_layout(self, filename):
+    def _generate_layout(self, filename, extra_kwargs):
         self.filename = filename
         self.layout, self.dimensions = get_page_layout(
-            self.filename,
-            char_margin=self.char_margin,
-            line_margin=self.line_margin,
-            word_margin=self.word_margin)
+            self.filename, **self.extra_kwargs)
         self.horizontal_text = get_text_objects(self.layout, ltype="lh")
         self.vertical_text = get_text_objects(self.layout, ltype="lv")
         self.pdf_width, self.pdf_height = self.dimensions

camelot/parsers/lattice.py

@@ -348,8 +348,8 @@ class Lattice(BaseParser):
 
         return table
 
-    def extract_tables(self, filename, suppress_stdout=False):
-        self._generate_layout(filename)
+    def extract_tables(self, filename, suppress_stdout=False, extra_kwargs={}):
+        self._generate_layout(filename, extra_kwargs)
         if not suppress_stdout:
             logger.info('Processing {}'.format(os.path.basename(self.rootname)))
 

camelot/parsers/stream.py

@@ -388,8 +388,8 @@ class Stream(BaseParser):
 
         return table
 
-    def extract_tables(self, filename, suppress_stdout=False):
-        self._generate_layout(filename)
+    def extract_tables(self, filename, suppress_stdout=False, extra_kwargs={}):
+        self._generate_layout(filename, extra_kwargs)
         if not suppress_stdout:
             logger.info('Processing {}'.format(os.path.basename(self.rootname)))
 

camelot/utils.py

@@ -558,7 +558,7 @@ def compute_whitespace(d):
 
 
 def get_page_layout(filename, char_margin=1.0, line_margin=0.5, word_margin=0.1,
-               detect_vertical=True, all_texts=True):
+                    detect_vertical=True, all_texts=True):
     """Returns a PDFMiner LTPage object and page dimension of a single
     page pdf. See https://euske.github.io/pdfminer/ to get definitions
     of kwargs.