您的位置:首页 -> 软件教程 -> 编程开发 -> 编程工具
软件教程分类查找
办公软件 图形图像 视频播放 格式转换 手机辅助 系统工具 电脑学习 下载工具 浏览器 QQ 专区 聊天 输入法 安全杀毒
第一部分 基础教程
精品软件课程
更多>>

python实现将html表格转换成CSV文件

6.0
出处:2345软件大全 时间:2018-03-06 人气:53

核心提示:本文实例讲述了python实现将html表格转换成CSV文件的方法。

  本文实例讲述了python实现将html表格转换成CSV文件的方法。分享给大家供大家参考。

python实现将html表格转换成CSV文件

  具体如下:  使用方法:python html2csv.py *.html  这段代码使用了 HTMLParser 模块  ?

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

#!/usr/bin/python

# -*- coding: iso-8859-1 -*-

# Hello, this program is written in Python - http://python.org

programname = 'html2csv - version 2002-09-20 - http://sebsauvage.net'

import sys, getopt, os.path, glob, HTMLParser, re

try: import psyco ; psyco.jit() # If present, use psyco to accelerate the program

except: pass

def usage(progname):

''' Display program usage. '''

progname = os.path.split(progname)[1]

if os.path.splitext(progname)[1] in ['.py','.pyc']: progname = 'python '+progname

return '''%s

A coarse HTML tables to CSV (Comma-Separated Values) converter.

Syntax : %s source.html

Arguments : source.html is the HTML file you want to convert to CSV.

By default, the file will be converted to csv with the same

name and the csv extension (source.html -> source.csv)

You can use * and ?.

Examples : %s mypage.html

: %s *.html

This program is public domain.

Author : Sebastien SAUVAGE <sebsauvage at sebsauvage dot net>

http://sebsauvage.net

''' % (programname, progname, progname, progname)

class html2csv(HTMLParser.HTMLParser):

''' A basic parser which converts HTML tables into CSV.

Feed HTML with feed(). Get CSV with getCSV(). (See example below.)

All tables in HTML will be converted to CSV (in the order they occur

in the HTML file).

You can process very large HTML files by feeding this class with chunks

of html while getting chunks of CSV by calling getCSV().

Should handle badly formated html (missing <tr>, </tr>, </td>,

extraneous </td>, </tr>...).

This parser uses HTMLParser from the HTMLParser module,

not HTMLParser from the htmllib module.

Example: parser = html2csv()

parser.feed( open('mypage.html','rb').read() )

open('mytables.csv','w+b').write( parser.getCSV() )

This class is public domain.

Author: Sébastien SAUVAGE <sebsauvage at sebsauvage dot net>

http://sebsauvage.net

Versions:

2002-09-19 : - First version

2002-09-20 : - now uses HTMLParser.HTMLParser instead of htmllib.HTMLParser.

- now parses command-line.

To do:

- handle <PRE> tags

- convert html entities (&name; and &#ref;) to Ascii.

'''

def __init__(self):

HTMLParser.HTMLParser.__init__(self)

self.CSV = '' # The CSV data

self.CSVrow = '' # The current CSV row beeing constructed from HTML

self.inTD = 0 # Used to track if we are inside or outside a <TD>...</TD> tag.

self.inTR = 0 # Used to track if we are inside or outside a <TR>...</TR> tag.

self.re_multiplespaces = re.compile('s+') # regular expression used to remove spaces in excess

self.rowCount = 0 # CSV output line counter.

def handle_starttag(self, tag, attrs):

if tag == 'tr': self.start_tr()

elif tag == 'td': self.start_td()

def handle_endtag(self, tag):

if tag == 'tr': self.end_tr()

elif tag == 'td': self.end_td()

def start_tr(self):

if self.inTR: self.end_tr() # <TR> implies </TR>

self.inTR = 1

def end_tr(self):

if self.inTD: self.end_td() # </TR> implies </TD>

self.inTR = 0

if len(self.CSVrow) > 0:

self.CSV += self.CSVrow[:-1]

self.CSVrow = ''

self.CSV += 'n'

self.rowCount += 1

def start_td(self):

if not self.inTR: self.start_tr() # <TD> implies <TR>

self.CSVrow += '"'

self.inTD = 1

def end_td(self):

if self.inTD:

self.CSVrow += '",'

self.inTD = 0

def handle_data(self, data):

if self.inTD:

self.CSVrow += self.re_multiplespaces.sub(' ',data.replace('t',' ').replace('n','').replace('r','').replace('"','""'))

def getCSV(self,purge=False):

''' Get output CSV.

If purge is true, getCSV() will return all remaining data,

even if <td> or <tr> are not properly closed.

(You would typically call getCSV with purge=True when you do not have

any more HTML to feed and you suspect dirty HTML (unclosed tags). '''

if purge and self.inTR: self.end_tr() # This will also end_td and append last CSV row to output CSV.

dataout = self.CSV[:]

self.CSV = ''

return dataout

if __name__ == "__main__":

try: # Put getopt in place for future usage.

opts, args = getopt.getopt(sys.argv[1:],None)

except getopt.GetoptError:

print usage(sys.argv[0]) # print help information and exit:

sys.exit(2)

if len(args) == 0:

print usage(sys.argv[0]) # print help information and exit:

sys.exit(2)

print programname

html_files = glob.glob(args[0])

for htmlfilename in html_files:

outputfilename = os.path.splitext(htmlfilename)[0]+'.csv'

parser = html2csv()

print 'Reading %s, writing %s...' % (htmlfilename, outputfilename)

try:

htmlfile = open(htmlfilename, 'rb')

csvfile = open( outputfilename, 'w+b')

data = htmlfile.read(8192)

while data:

parser.feed( data )

csvfile.write( parser.getCSV() )

sys.stdout.write('%d CSV rows written.r' % parser.rowCount)

data = htmlfile.read(8192)

csvfile.write( parser.getCSV(True) )

csvfile.close()

htmlfile.close()

except:

print 'Error converting %s ' % htmlfilename

try: htmlfile.close()

except: pass

try: csvfile.close()

except: pass

print 'All done. '

  希望本文所述对大家的Python程序设计有所帮助。