Briq
/
camelot-py
6
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Optimised and cleaned the code.

pull/280/head
pratheeshraniprakash 2022-01-05 12:56:30 +05:30
parent 644bbe7c6d
commit 8beb8d79bf
7 changed files with 43 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored
View File

@ -1,5 +1,5 @@
fontconfig/
__pycache__/
__pycache__/*
*.py[cod]
*.so
@ -18,3 +18,5 @@ htmlcov/
# vscode
.vscode
.env
changelog.txt

2
CODE_OF_CONDUCT.md
View File

@ -1,3 +1,3 @@
Be cordial or be on your way. --Kenneth Reitz
https://www.kennethreitz.org/essays/be-cordial-or-be-on-your-way
https://kennethreitz.org/essays/2013/01/27/be-cordial-or-be-on-your-way

2
CONTRIBUTING.md
View File

@ -10,7 +10,7 @@ The following quote sums up the **Code Of Conduct**.
> Be cordial or be on your way. --Kenneth Reitz
Kenneth Reitz has also written an [essay](https://www.kennethreitz.org/essays/be-cordial-or-be-on-your-way) on this topic, which you should read.
Kenneth Reitz has also written an [essay](https://kennethreitz.org/essays/2013/01/27/be-cordial-or-be-on-your-way) on this topic, which you should read.
As the [Requests Code Of Conduct](http://docs.python-requests.org/en/master/dev/contributing/#be-cordial) states, **all contributions are welcome**, as long as everyone involved is treated with respect.

12
camelot/core.py
View File

@ -524,12 +524,12 @@ class Table(object):
def set_border(self):
"""Sets table border edges to True."""
for r in range(len(self.rows)):
self.cells[r][0].left = True
self.cells[r][len(self.cols) - 1].right = True
for c in range(len(self.cols)):
self.cells[0][c].top = True
self.cells[len(self.rows) - 1][c].bottom = True
for index, row in enumerate(self.rows):
self.cells[index][0].left = True
self.cells[index][len(self.cols) - 1].right = True
for index, col in enumerate(self.cols):
self.cells[0][index].top = True
self.cells[len(self.rows) - 1][index].bottom = True
return self
def set_span(self):

4
camelot/handlers.py
View File

@ -35,9 +35,7 @@ class PDFHandler(object):
"""
def __init__(self, filepath, pages="1", password=None):
if is_url(filepath):
filepath = download_url(filepath)
self.filepath = filepath
self.filepath = download_url(filepath) if is_url(filepath) else filepath
if not filepath.lower().endswith(".pdf"):
raise NotImplementedError("File format not supported")

58
camelot/parsers/lattice.py
View File

@ -162,7 +162,7 @@ class Lattice(BaseParser):
return backend
@staticmethod
def _reduce_index(t, idx, shift_text):
def _reduce_index(table, idx, shift_text):
"""Reduces index of a text object if it lies within a spanning
cell.
@ -187,32 +187,28 @@ class Lattice(BaseParser):
indices = []
for r_idx, c_idx, text in idx:
for d in shift_text:
if d == "l":
if t.cells[r_idx][c_idx].hspan:
while not t.cells[r_idx][c_idx].left:
c_idx -= 1
if d == "r":
if t.cells[r_idx][c_idx].hspan:
while not t.cells[r_idx][c_idx].right:
c_idx += 1
if d == "t":
if t.cells[r_idx][c_idx].vspan:
while not t.cells[r_idx][c_idx].top:
r_idx -= 1
if d == "b":
if t.cells[r_idx][c_idx].vspan:
while not t.cells[r_idx][c_idx].bottom:
r_idx += 1
if d == "l" and table.cells[r_idx][c_idx].hspan:
while not table.cells[r_idx][c_idx].left:
c_idx -= 1
if d == "r" and table.cells[r_idx][c_idx].hspan:
while not table.cells[r_idx][c_idx].right:
c_idx += 1
if d == "t" and table.cells[r_idx][c_idx].vspan:
while not table.cells[r_idx][c_idx].top:
r_idx -= 1
if d == "b" and table.cells[r_idx][c_idx].vspan:
while not table.cells[r_idx][c_idx].bottom:
r_idx += 1
indices.append((r_idx, c_idx, text))
return indices
@staticmethod
def _copy_spanning_text(t, copy_text=None):
def _copy_spanning_text(table, copy_text=None):
"""Copies over text in empty spanning cells.
Parameters
----------
t : camelot.core.Table
table : camelot.core.Table
copy_text : list, optional (default: None)
{'h', 'v'}
Select one or more strings from above and pass them as a list
@ -221,23 +217,23 @@ class Lattice(BaseParser):
Returns
-------
t : camelot.core.Table
table : camelot.core.Table
"""
for f in copy_text:
if f == "h":
for i in range(len(t.cells)):
for j in range(len(t.cells[i])):
if t.cells[i][j].text.strip() == "":
if t.cells[i][j].hspan and not t.cells[i][j].left:
t.cells[i][j].text = t.cells[i][j - 1].text
for i in range(len(table.cells)):
for j in range(len(table.cells[i])):
if table.cells[i][j].text.strip() == "":
if table.cells[i][j].hspan and not table.cells[i][j].left:
table.cells[i][j].text = table.cells[i][j - 1].text
elif f == "v":
for i in range(len(t.cells)):
for j in range(len(t.cells[i])):
if t.cells[i][j].text.strip() == "":
if t.cells[i][j].vspan and not t.cells[i][j].top:
t.cells[i][j].text = t.cells[i - 1][j].text
return t
for i in range(len(table.cells)):
for j in range(len(table.cells[i])):
if table.cells[i][j].text.strip() == "":
if table.cells[i][j].vspan and not table.cells[i][j].top:
table.cells[i][j].text = table.cells[i - 1][j].text
return table
def _generate_table_bbox(self):
def scale_areas(areas):

5
camelot/utils.py
View File

@ -81,7 +81,10 @@ def download_url(url):
"""
filename = f"{random_string(6)}.pdf"
with tempfile.NamedTemporaryFile("wb", delete=False) as f:
headers = {"User-Agent": "Mozilla/5.0"}
headers = {
"User-Agent": "Mozilla/5.0",
"Accept-Encoding": "gzip;q=1.0, deflate;q=0.9, br;q=0.8, compress;q=0.7, *;q=0.1"
}
request = Request(url, None, headers)
obj = urlopen(request)
content_type = obj.info().get_content_type()