Initial commit

.gitignore

@@ -0,0 +1,60 @@
+notebooks/
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/

LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2015, Jeremy Singer-Vine
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,43 @@
+__WARNING: This software is in its very early days, might not work well, and might change dramatically in future versions.__
+
+# PDFPlumber
+
+Plumb a PDF for detailed information about each char, rectangle, line, et cetera.
+
+Built on [`pdfminer`](https://github.com/euske/pdfminer)/[`pdfminer.six`](https://github.com/goulu/pdfminer).
+
+## Installation
+
+```sh
+pip install git+https://github.com/goulu/pdfminer#egg=pdfminer.six
+pip install pdfplumber
+```
+
+## Usage
+
+```python
+import pdfplumber
+
+pdf = pdfplumber.from_path("path/to/file.pdf")
+
+# OR
+
+with open("path/to/file.pdf") as f:
+    pdf = pdfplumber.load(f)
+
+print(pdf.chars)
+print(pdf.rects)
+print(pdf.lines)
+```
+
+### Pandas Integration
+
+By default, `pdf.chars`, etc., will be a plain Python dictionary. But if you `pandas=True` to `pdfplumber.load`/`.from_file`, you'll receive those properties as [Pandas dataframes](http://pandas.pydata.org/pandas-docs/stable/dsintro.html#dataframe). 
+
+## Python Support
+
+Support for Python 3 is rough around the edges and largely dependent on the progress of [`pdfminer.six`](https://github.com/goulu/pdfminer).
+
+## Feedback
+
+Issues and pull requests welcome.

pdfplumber/__init__.py

@@ -0,0 +1,16 @@
+from pdfplumber.pdf import PDF
+import pdfminer
+import pdfminer.pdftypes
+pdfminer.pdftypes.STRICT = False
+
+def load(file_or_buffer, **kwargs):
+    return PDF(file_or_buffer, **kwargs)
+
+def from_path(path, **kwargs):
+    with open(path, "rb") as f:
+        return PDF(f, **kwargs)
+
+def set_debug(debug=0):
+    pdfminer.debug = debug
+
+set_debug(0)

pdfplumber/pdf.py

@@ -0,0 +1,125 @@
+from six import string_types
+from six.moves import cStringIO
+
+try:
+    import pandas
+except: pass
+
+from pdfminer.pdfparser import PDFParser
+from pdfminer.pdfdocument import PDFDocument
+from pdfminer.pdfpage import PDFPage
+from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
+from pdfminer.layout import LAParams, LTChar, LTImage, LTPage
+from pdfminer.converter import PDFPageAggregator
+
+class PDF(object):
+    def __init__(self, file_or_buffer, pandas=False, laparams={}):
+        self.pandas = pandas
+        self.laparams = LAParams(**laparams)
+
+        rsrcmgr = PDFResourceManager()
+        self.doc = PDFDocument(PDFParser(file_or_buffer))
+        self.device = PDFPageAggregator(rsrcmgr, laparams=self.laparams)
+        self.interpreter = PDFPageInterpreter(rsrcmgr, self.device)
+
+        self.pages = []
+        for page in PDFPage.create_pages(self.doc):
+            self.interpreter.process_page(page)
+            layout = self.device.get_result()
+            self.pages.append(layout)
+
+        self.objects = self.parse()
+
+    def parse(self):
+        try:
+            # pdfminer < 20131022
+            _pages = self.doc.get_pages()
+        except AttributeError:
+            # pdfminer >= 20131022
+            _pages = PDFPage.create_pages(self.doc)
+
+        objects = {}
+
+        def process_object(obj, page):
+            _round = lambda x: round(x, 3) if type(x) == float else x
+
+            attr = dict((k, _round(v)) for k, v in obj.__dict__.items()
+                if isinstance(v, (float, int, string_types))
+                    and k[0] != "_")
+
+            kind = obj.__class__.__name__
+            attr["kind"] = kind
+            attr["pageid"] = page.pageid
+
+            if hasattr(obj, "get_text"):
+                attr["text"] = obj.get_text()
+
+            if attr.get("y0") != None:
+                page_index = self.pages.index(page)
+                prev_h = sum(p.height for p in self.pages[:page_index])
+                attr["top"] = _round(page.height - attr["y1"])
+                attr["doctop"] = _round(prev_h + attr["top"])
+
+            if objects.get(kind) == None:
+                objects[kind] = []
+            objects[kind].append(attr)
+
+            if hasattr(obj, "_objs"):
+                for child in obj._objs:
+                    process_object(child, page)
+        
+        def process_page(page):
+            for child in page._objs:
+                process_object(child, page)
+
+        for page in self.pages:
+            process_page(page)
+
+        return objects
+
+    def emit(self, objs):
+        return pandas.DataFrame(objs) if self.pandas else objs
+        
+    @property
+    def rects(self):
+        x = self.objects.get("LTRect", [])
+        return self.emit(x)
+
+    @property
+    def lines(self):
+        x = self.objects.get("LTLine", [])
+        return self.emit(x)
+
+    @property
+    def images(self):
+        x = self.objects.get("LTImage", [])
+        return self.emit(x)
+
+    @property
+    def figures(self):
+        x = self.objects.get("LTFigure", [])
+        return self.emit(x)
+
+    @property
+    def chars(self):
+        x = self.objects.get("LTChar", [])
+        return self.emit(x)
+
+    @property
+    def annos(self):
+        x = self.objects.get("LTAnno", [])
+        return self.emit(x)
+
+    @property
+    def text_lines(self):
+        h = self.objects.get("LTTextLineHorizontal", [])
+        v = self.objects.get("LTTextLineVertical", [])
+        x = h + v
+        return self.emit(x)
+
+    @property
+    def text_boxes(self):
+        h = self.objects.get("LTTextBoxHorizontal", [])
+        v = self.objects.get("LTTextBoxVertical", [])
+        x = h + v
+        return self.emit(x)

setup.py

@@ -0,0 +1,16 @@
+import sys, os
+from setuptools import setup, find_packages
+import subprocess
+
+base_reqs = [
+    "chardet",
+    "pdfminer.six"
+]
+
+setup(
+    name="pdfplumber",
+    version="0.0.0",
+    packages=find_packages(exclude=["test",]),
+    tests_require=[ "nose", "pandas" ] + base_reqs,
+    install_requires=base_reqs,
+)

tox.ini

@@ -0,0 +1,8 @@
+[tox]
+envlist = py27,py31,py34
+
+[testenv]
+deps=nose
+     pandas
+     git+https://github.com/goulu/pdfminer#egg=pdfminer.six
+commands=nosetests