8000 read_html: Handle colspan and rowspan by adamhooper · Pull Request #21487 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

read_html: Handle colspan and rowspan #21487

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
Jul 5, 2018
Merged

read_html: Handle colspan and rowspan #21487

Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
3e58794
Handle colspan and rowspan
adamhooper Jun 14, 2018
f89b32a
Fixes after code review -- thanks, @WillAyd
adamhooper Jun 15, 2018
34f87cb
Docstring tweaks
adamhooper Jun 15, 2018
582c86b
Details -- thanks, @jreback
adamhooper Jun 15, 2018
d2f0b83
Tweak comments
adamhooper Jun 15, 2018
74c2384
Address latest review comments from @WillAyd
adamhooper Jun 15, 2018
ad6e869
Clean up html tests
adamhooper Jun 21, 2018
6fa0489
Do not nix rows of empty
adamhooper Jun 21, 2018
86b2dea
Merge branch 'master' into colspan-rowspan
adamhooper Jul 2, 2018
d4f4bb1
Comments: Notes after Returns
adamhooper Jul 3, 2018
e296bd1
Document read_html changes in whatsnew
adamhooper Jul 4, 2018
f0f91c3
Merge branch 'master' into colspan-rowspan
adamhooper Jul 4, 2018
95ce993
Improve whatsnew with ipython
adamhooper Jul 4, 2018
5fd863b
fixup whatsnew
jreback Jul 5, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Docstring tweaks
  • Loading branch information
@adamhooper
adamhooper committed Jun 27, 2018
commit 34f87cb9338385f91d3df204b666e7dd5b8cfb65
34 changes: 20 additions & 14 deletions pandas/io/html.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,7 +214,7 @@ def parse_tables(self):

Returns
-------
tables : list of parsed (header, body, footer) tuples from tables
list of parsed (header, body, footer) tuples from tables.
"""
tables = self._parse_tables(self._build_doc(), self.match, self.attrs)
return (self._parse_thead_tbody_tfoot(table) for table in tables)
Expand All @@ -233,7 +233,7 @@ def _attr_getter(self, obj, attr):

Returns
-------
text : str or unicode
str or unicode
The attribute value.
"""
raise com.AbstractMethodError(self)
Expand Down Expand Up @@ -264,7 +264,7 @@ def _parse_td(self, obj):

Returns
-------
columns : list of node-like
list of node-like
These are the elements of each row, i.e., the columns.
"""
raise com.AbstractMethodError(self)
Expand All @@ -279,7 +279,8 @@ def _parse_thead_tr(self, table):

Returns
-------
rows : list of <tr> row elements of a table
list of node-like
These are the <tr> row elements of a table.
"""
raise com.AbstractMethodError(self)

Expand All @@ -297,7 +298,8 @@ def _parse_tbody_tr(self, table):

Returns
-------
rows : list of <tr> row elements of a table
list of node-like
These are the <tr> row elements of a table.
"""
raise com.AbstractMethodError(self)

Expand All @@ -311,7 +313,8 @@ def _parse_tfoot_tr(self, table):

Returns
-------
rows : list of <tr> row elements of a table
list of node-like
These are the <tr> row elements of a table.
"""
raise com.AbstractMethodError(self)

Expand All @@ -336,7 +339,8 @@ def _parse_tables(self, doc, match, attrs):

Returns
-------
tables : list of HTML <table> elements to be parsed into raw data.
list of node-like
HTML <table> elements to be parsed into raw data.
"""
raise com.AbstractMethodError(self)

Expand All @@ -354,8 +358,8 @@ def _equals_tag(self, obj, tag):

Returns
-------
is_tag_equal : boolean
boolean indicating if the object is equal to tag 'tag'
boolean
Whether the object is equal to tag 'tag'
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Parameter references are typically done in backticks on docstrings, so you can change "tag 'tag'" to simply "`tag`"

"""
raise com.AbstractMethodError(self)

Expand All @@ -365,7 +369,8 @@ def _build_doc(self):

Returns
-------
obj : the DOM from which to parse the table element.
node-like
The DOM from which to parse the table element.
"""
raise com.AbstractMethodError(self)

Expand All @@ -390,7 +395,7 @@ def _parse_thead_tbody_tfoot(self, table_html):

Returns
-------
tuple of (header, body, footer)
tuple of (header, body, footer), each a list of list-of-text rows.
"""

header_rows = self._parse_thead_tr(table_html)
Expand Down Expand Up @@ -432,7 +437,8 @@ def _expand_colspan_rowspan(self, rows):

Returns
-------
res : list of rows, each of which is a list of str in that row
list of list
Each returned row is a list of str text.
"""

all_texts = [] # list of rows, each a list of str
Expand Down Expand Up @@ -501,14 +507,14 @@ def _handle_hidden_tables(self, tbl_list, attr_name):

Parameters
----------
tbl_list : list of Tag or list of Element
tbl_list : list of node-like
Type of list elements will vary depending upon parser used
attr_name : str
Name of the accessor for retrieving HTML attributes

Returns
-------
list of Tag or list of Element
list of node-like
Return type matches `tbl_list`
"""
if not self.displayed_only:
Expand Down
0