from mechanize import Browser
br = Browser()
br.open('http://somewebpage')
html = br.response().readlines()
for line in html:
print line
当在HTML文件中打印一行时，我试图找到一种方法，只显示每个HTML元素的内容，而不是格式本身。如果它发现'<a href="等等。例如">some text</a>'，它只会打印'some text'， '<b>hello</b>'打印'hello'，等等。该怎么做呢?
当前回答
这是一个快速修复，甚至可以更优化，但它将工作良好。这段代码将用""替换所有非空标记，并从给定的输入文本中剥离所有html标记。你可以使用./file.py输入输出运行它
#!/usr/bin/python
import sys
def replace(strng,replaceText):
rpl = 0
while rpl > -1:
rpl = strng.find(replaceText)
if rpl != -1:
strng = strng[0:rpl] + strng[rpl + len(replaceText):]
return strng
lessThanPos = -1
count = 0
listOf = []
try:
#write File
writeto = open(sys.argv[2],'w')
#read file and store it in list
f = open(sys.argv[1],'r')
for readLine in f.readlines():
listOf.append(readLine)
f.close()
#remove all tags
for line in listOf:
count = 0;
lessThanPos = -1
lineTemp = line
for char in lineTemp:
if char == "<":
lessThanPos = count
if char == ">":
if lessThanPos > -1:
if line[lessThanPos:count + 1] != '<>':
lineTemp = replace(lineTemp,line[lessThanPos:count + 1])
lessThanPos = -1
count = count + 1
lineTemp = lineTemp.replace("<","<")
lineTemp = lineTemp.replace(">",">")
writeto.write(lineTemp)
writeto.close()
print "Write To --- >" , sys.argv[2]
except:
print "Help: invalid arguments or exception"
print "Usage : ",sys.argv[0]," inputfile outputfile"
其他回答
# This is a regex solution.
import re
def removeHtml(html):
if not html: return html
# Remove comments first
innerText = re.compile('<!--[\s\S]*?-->').sub('',html)
while innerText.find('>')>=0: # Loop through nested Tags
text = re.compile('<[^<>]+?>').sub('',innerText)
if text == innerText:
break
innerText = text
return innerText.strip()
您可以使用不同的HTML解析器(如lxml或Beautiful Soup)——它提供只提取文本的函数。或者，您可以在行字符串上运行一个regex来删除标记。请参阅Python文档了解更多信息。
使用BeautifulSoup, html2text或来自@Eloff的代码，大多数时候，它仍然是一些html元素，javascript代码…
所以你可以使用这些库的组合并删除markdown格式(Python 3):
import re
import html2text
from bs4 import BeautifulSoup
def html2Text(html):
def removeMarkdown(text):
for current in ["^[ #*]{2,30}", "^[ ]{0,30}\d\\\.", "^[ ]{0,30}\d\."]:
markdown = re.compile(current, flags=re.MULTILINE)
text = markdown.sub(" ", text)
return text
def removeAngular(text):
angular = re.compile("[{][|].{2,40}[|][}]|[{][*].{2,40}[*][}]|[{][{].{2,40}[}][}]|\[\[.{2,40}\]\]")
text = angular.sub(" ", text)
return text
h = html2text.HTML2Text()
h.images_to_alt = True
h.ignore_links = True
h.ignore_emphasis = False
h.skip_internal_links = True
text = h.handle(html)
soup = BeautifulSoup(text, "html.parser")
text = soup.text
text = removeAngular(text)
text = removeMarkdown(text)
return text
这对我来说很有效，但当然还可以增强……
我就是这么做的，但我不知道我在做什么。我通过剥离HTML标记从HTML表中获取数据。
它接受字符串“name”并返回不带HTML标记的字符串“name1”。
x = 0
anglebrackets = 0
name1 = ""
while x < len(name):
if name[x] == "<":
anglebrackets = anglebrackets + 1
if name[x] == ">":
anglebrackets = anglebrackets - 1
if anglebrackets == 0:
if name[x] != ">":
name1 = name1 + name[x]
x = x + 1
我总是使用这个函数来剥离HTML标签，因为它只需要Python标准库:
对于Python 3:
from io import StringIO
from html.parser import HTMLParser
class MLStripper(HTMLParser):
def __init__(self):
super().__init__()
self.reset()
self.strict = False
self.convert_charrefs= True
self.text = StringIO()
def handle_data(self, d):
self.text.write(d)
def get_data(self):
return self.text.getvalue()
def strip_tags(html):
s = MLStripper()
s.feed(html)
return s.get_data()
对于Python 2:
from HTMLParser import HTMLParser
from StringIO import StringIO
class MLStripper(HTMLParser):
def __init__(self):
self.reset()
self.text = StringIO()
def handle_data(self, d):
self.text.write(d)
def get_data(self):
return self.text.getvalue()
def strip_tags(html):
s = MLStripper()
s.feed(html)
return s.get_data()
