pythontable处理_python处理html的table标签

import sys

import csv

import urllib2

import BeautifulSoup

#page = urllib2.urlopen(sys.argv[1]).read()

soup = BeautifulSoup.BeautifulSoup(open(sys.argv[1]).read())

csvout = csv.writer(sys.stdout)

for table in soup.findAll('table'):

print "

#print '#'

#print '# Table'

#print '# Fields: ' + ','.join([tr.text for tr in table.findAll('th')])

for row in table.findAll('tr'):

print "

"

#csvout.writerow([tr.text for tr in row.findAll('td')])

for tr in row.findAll('td'):

print "

"

print tr.text.encode("utf-8")

print "

"

print "

"

print "

"

break

#!/bin/bash

#process.h

basedir=$(dirname $1)

echo $basedir

#echo \

\\ >> $basedir/baobei.html

prodname=$(grep -o '

.*' $1 | cut -d \> -f 2 | cut -d \< -f 1)

prodname=$(echo $prodname | cut -d _ -f 1)

price=$(grep -o '[0-9]*' $1 | cut -d \> -f 2 | cut -d \< -f 1)

echo \

echo \

>> $basedir/baobei.html

echo \

Name\ >> $basedir/baobei.html

echo \

$prodname\ >> $basedir/baobei.html

echo \

>> $basedir/baobei.html

echo \

>> $basedir/baobei.html

echo \

Price\ >> $basedir/baobei.html

echo \

$price\ >> $basedir/baobei.html

echo \

>> $basedir/baobei.html

python ./printtab.py $1 >> $basedir/baobei.html

echo \

>>