我们的NightwatchJs测试开始因错误而失败
from bs4 import BeautifulSoup
from html import escape
from html.parser import HTMLParser
data = '''<root><level1><level2><field1>val1</field1><field2>val2</field2><field3>val3</field3></level2></level1></root>'''
class MyHTMLParser(HTMLParser):
def __init__(self):
super().__init__()
self.__t = 0
self.lines = []
self.__current_line = ''
self.__current_tag = ''
@staticmethod
def __attr_str(attrs):
return ' '.join('{}="{}"'.format(name, escape(value)) for (name, value) in attrs)
def handle_starttag(self, tag, attrs):
if tag != self.__current_tag:
self.lines += [self.__current_line]
self.__current_line = '\t' * self.__t + '<{}>'.format(tag + (' ' + self.__attr_str(attrs) if attrs else ''))
self.__current_tag = tag
self.__t += 1
def handle_endtag(self, tag):
self.__t -= 1
if tag != self.__current_tag:
self.lines += [self.__current_line]
self.lines += ['\t' * self.__t + '</{}>'.format(tag)]
else:
self.lines += [self.__current_line + '</{}>'.format(tag)]
self.__current_line = ''
def handle_data(self, data):
self.__current_line += data
def get_parsed_string(self):
return '\n'.join(l for l in self.lines if l)
parser = MyHTMLParser()
soup = BeautifulSoup(data, 'lxml')
print('BeautifulSoup prettify():')
print('*' * 80)
print(soup.root.prettify())
print('custom html parser:')
print('*' * 80)
parser.feed(str(soup.root))
print(parser.get_parsed_string())
我们正在使用docker设置带有Chrome节点的Selenium集线器/网格。关于如何降级到ChromeDriver 74版的想法吗?
答案 0 :(得分:0)
我通过为chrome节点选择特定图像来整理版本,从而临时修复了该版本:
BeautifulSoup prettify():
********************************************************************************
<root>
<level1>
<level2>
<field1>
val1
</field1>
<field2>
val2
</field2>
<field3>
val3
</field3>
</level2>
</level1>
</root>
custom html parser:
********************************************************************************
<root>
<level1>
<level2>
<field1>val1</field1>
<field2>val2</field2>
<field3>val3</field3>
</level2>
</level1>
</root>