用python将文本文件转换为html文件
我有一个文本文件,其中包含:用python将文本文件转换为html文件,python,html,text,Python,Html,Text,我有一个文本文件,其中包含: JavaScript 0 /AA 0 OpenAction 1 AcroForm 0 JBIG2Decode 0 RichMedia 0 Launch 0 Colors>2^24 0 uri
JavaScript 0
/AA 0
OpenAction 1
AcroForm 0
JBIG2Decode 0
RichMedia 0
Launch 0
Colors>2^24 0
uri 0
我编写了以下代码以将文本文件转换为html:
contents = open("C:\\Users\\Suleiman JK\\Desktop\\Static_hash\\test","r")
with open("suleiman.html", "w") as e:
for lines in contents.readlines():
e.write(lines + "<br>\n")
我应该怎么做才能使文本文件中的内容和两列相同,这是因为HTML解析器会折叠所有空白。有两种方法可以做到这一点(很可能更多) 一种是将其标记为“预格式化文本”,方法是将其放入
…
标记中
<table>
<tr><td>Javascript</td><td>0</td></tr>
...
</table>
另一个是桌子(这就是制作桌子的目的):
Javascript0
...
手工打字相当繁琐,但很容易从脚本生成。像这样的方法应该会奏效:
contents = open"C:\\Users\\Suleiman JK\\Desktop\\Static_hash\\test","r")
with open("suleiman.html", "w") as e:
for lines in contents.readlines():
e.write("<pre>" + lines + "</pre> <br>\n")
contents=open(“C:\\Users\\Suleiman JK\\Desktop\\Static\u hash\\test”,“r”)
以open(“suleiman.html”,“w”)作为e:
e、 写入(“\n”)
from bs4 import BeautifulSoup
soup = BeautifulSoup()
body = soup.new_tag('body')
soup.insert(0, body)
table = soup.new_tag('table')
body.insert(0, table)
with open('path/to/input/file.txt') as infile:
for line in infile:
row = soup.new_tag('tr')
col1, col2 = line.split()
for coltext in (col2, col1): # important that you reverse order
col = soup.new_tag('td')
col.string = coltext
row.insert(0, col)
table.insert(len(table.contents), row)
with open('path/to/output/file.html', 'w') as outfile:
outfile.write(soup.prettify())
对于contents.readlines()中的行:
e、 写入(“%s%s\n”%lines.split())
from bs4 import BeautifulSoup
soup = BeautifulSoup()
body = soup.new_tag('body')
soup.insert(0, body)
table = soup.new_tag('table')
body.insert(0, table)
with open('path/to/input/file.txt') as infile:
for line in infile:
row = soup.new_tag('tr')
col1, col2 = line.split()
for coltext in (col2, col1): # important that you reverse order
col = soup.new_tag('td')
col.string = coltext
row.insert(0, col)
table.insert(len(table.contents), row)
with open('path/to/output/file.html', 'w') as outfile:
outfile.write(soup.prettify())
e、 写入(“\n”)
from bs4 import BeautifulSoup
soup = BeautifulSoup()
body = soup.new_tag('body')
soup.insert(0, body)
table = soup.new_tag('table')
body.insert(0, table)
with open('path/to/input/file.txt') as infile:
for line in infile:
row = soup.new_tag('tr')
col1, col2 = line.split()
for coltext in (col2, col1): # important that you reverse order
col = soup.new_tag('td')
col.string = coltext
row.insert(0, col)
table.insert(len(table.contents), row)
with open('path/to/output/file.html', 'w') as outfile:
outfile.write(soup.prettify())
只需将代码更改为包含
和
标记,以确保文本的格式与原始文本文件中的格式相同
from jinja2 import Template
c = '''<!doctype html>
<html>
<head>
<title>My Title</title>
</head>
<body>
<table>
<thead>
<tr><th>Col 1</th><th>Col 2</th></tr>
</thead>
<tbody>
{% for col1, col2 in lines %}
<tr><td>{{ col 1}}</td><td>{{ col2 }}</td></tr>
{% endfor %}
</tbody>
</table>
</body>
</html>'''
t = Template(c)
lines = []
with open('yourfile.txt', 'r') as f:
for line in f:
lines.append(line.split())
with open('results.html', 'w') as f:
f.write(t.render(lines=lines))
header = '<!doctyle html><html><head><title>My Title</title></head><body>'
body = '<table><thead><tr><th>Col 1</th><th>Col 2</th></tr>'
footer = '</table></body></html>'
with open('input.txt', 'r') as input, open('output.html', 'w') as output:
output.writeln(header)
output.writeln(body)
for line in input:
col1, col2 = line.rstrip().split()
output.write('<tr><td>{}</td><td>{}</td></tr>\n'.format(col1, col2))
output.write(footer)
contents=open“C:\\Users\\Suleiman JK\\Desktop\\Static\u hash\\test”,“r”)
以open(“suleiman.html”,“w”)作为e:
对于contents.readlines()中的行:
e、 写(“+行+”
\n)
from bs4 import BeautifulSoup
soup = BeautifulSoup()
body = soup.new_tag('body')
soup.insert(0, body)
table = soup.new_tag('table')
body.insert(0, table)
with open('path/to/input/file.txt') as infile:
for line in infile:
row = soup.new_tag('tr')
col1, col2 = line.split()
for coltext in (col2, col1): # important that you reverse order
col = soup.new_tag('td')
col.string = coltext
row.insert(0, col)
table.insert(len(table.contents), row)
with open('path/to/output/file.html', 'w') as outfile:
outfile.write(soup.prettify())
您可以使用像或这样的独立模板库。以下是jinja的一个例子:
<?xml version="1.0" encoding="utf-8"?>
<body>
<table>
<p>
MUTHU PAGE
</p>
<tr>
<td>
2019/08/19 19:59:25 MUTHUKUMAR_TIME_DATE,line: 118 INFO | Logger object created for: MUTHUKUMAR_APP_USER_SIGNUP_LOG
</td>
</tr>
<tr>
<td>
2019/08/19 19:59:25 MUTHUKUMAR_DB_USER_SIGN_UP,line: 48 INFO | ***** User SIGNUP page start *****
</td>
</tr>
<tr>
<td>
2019/08/19 19:59:25 MUTHUKUMAR_DB_USER_SIGN_UP,line: 49 INFO | Enter first name: [Alphabet character only allowed, minimum 3 character to maximum 20 chracter]
这是HTML--使用BeautifulSoup
我已经添加了标题,在这里一行一行地循环,并在
发布所需的输出html的内容应该与上面的文本文件相同,有两列。您的意思是编辑原始文本文件,使每列之间的空格更少吗?原始文本文件的每行之间没有空格,但在html中,行与行之间有一个双空格从第二行删除您的
标记e.write()调用中的文本。
from bs4 import BeautifulSoup
soup = BeautifulSoup()
body = soup.new_tag('body')
soup.insert(0, body)
table = soup.new_tag('table')
body.insert(0, table)
with open('path/to/input/file.txt') as infile:
for line in infile:
row = soup.new_tag('tr')
col1, col2 = line.split()
for coltext in (col2, col1): # important that you reverse order
col = soup.new_tag('td')
col.string = coltext
row.insert(0, col)
table.insert(len(table.contents), row)
with open('path/to/output/file.html', 'w') as outfile:
outfile.write(soup.prettify())