1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
"""
Table factories
"""
import csv
from .prettytable import PrettyTable
from ._compact import py3k, HTMLParser
def from_csv(fp, field_names=None, **kwargs):
fmtparams = {}
for param in ["delimiter", "doublequote", "escapechar", "lineterminator",
"quotechar", "quoting", "skipinitialspace", "strict"]:
if param in kwargs:
fmtparams[param] = kwargs.pop(param)
if fmtparams:
reader = csv.reader(fp, **fmtparams)
else:
dialect = csv.Sniffer().sniff(fp.read(1024))
fp.seek(0)
reader = csv.reader(fp, dialect)
table = PrettyTable(**kwargs)
if field_names:
table.field_names = field_names
else:
if py3k:
table.field_names = [x.strip() for x in next(reader)]
else:
table.field_names = [x.strip() for x in reader.next()]
for row in reader:
table.add_row([x.strip() for x in row])
return table
def from_db_cursor(cursor, **kwargs):
if cursor.description:
table = PrettyTable(**kwargs)
table.field_names = [col[0] for col in cursor.description]
for row in cursor.fetchall():
table.add_row(row)
return table
class TableHandler(HTMLParser):
def __init__(self, **kwargs):
HTMLParser.__init__(self)
self.kwargs = kwargs
self.tables = []
self.last_row = []
self.rows = []
self.max_row_width = 0
self.active = None
self.last_content = ""
self.is_last_row_header = False
self.colspan = 0
def handle_starttag(self, tag, attrs):
self.active = tag
if tag == "th":
self.is_last_row_header = True
for (key, value) in attrs:
if key == "colspan":
self.colspan = int(value)
def handle_endtag(self, tag):
if tag in ["th", "td"]:
stripped_content = self.last_content.strip()
self.last_row.append(stripped_content)
if self.colspan:
for i in range(1, self.colspan):
self.last_row.append("")
self.colspan = 0
if tag == "tr":
self.rows.append(
(self.last_row, self.is_last_row_header))
self.max_row_width = max(self.max_row_width, len(self.last_row))
self.last_row = []
self.is_last_row_header = False
if tag == "table":
table = self.generate_table(self.rows)
self.tables.append(table)
self.rows = []
self.last_content = " "
self.active = None
def handle_data(self, data):
self.last_content += data
def generate_table(self, rows):
"""
Generates from a list of rows a PrettyTable object.
"""
table = PrettyTable(**self.kwargs)
for row in self.rows:
if len(row[0]) < self.max_row_width:
appends = self.max_row_width - len(row[0])
for i in range(1, appends):
row[0].append("-")
if row[1] is True:
self.make_fields_unique(row[0])
table.field_names = row[0]
else:
table.add_row(row[0])
return table
def make_fields_unique(self, fields):
"""
iterates over the row and make each field unique
"""
for i in range(0, len(fields)):
for j in range(i + 1, len(fields)):
if fields[i] == fields[j]:
fields[j] += "'"
def from_html(html_code, **kwargs):
"""
Generates a list of PrettyTables from a string of HTML code. Each <table> in
the HTML becomes one PrettyTable object.
"""
parser = TableHandler(**kwargs)
parser.feed(html_code)
return parser.tables
def from_html_one(html_code, **kwargs):
"""
Generates a PrettyTables from a string of HTML code which contains only a
single <table>
"""
tables = from_html(html_code, **kwargs)
try:
assert len(tables) == 1
except AssertionError:
raise Exception("More than one <table> in provided HTML code! Use from_html instead.")
return tables[0]
|
