首页
>
精通Python网络编程 > 爬虫代码测试文章
- 彻底掌握Python中的网络编程
- 已经是最后一篇了
# __author__ = 薯条老师
# __date__ = 2020-12-16
import re
class HTMLParser:
class Label:
def __init__(self, label, text, **kwargs):
self.__label = label
self.__text = text
self.__build_attrs(**kwargs)
def __build_attrs(self, **kwargs):
for name,value in kwargs.items():
self.__dict__[name] = value
def get_text(self):
return re.sub("<.*?>|</.*?>", "", self.__text)
def __getitem__(self, name):
if name == "text" and name not in self.__dict__:
self.__dict__[name] = self.get_text()
return self.__dict__.get(name)
def __init__(self, html):
self.__html = html
@property
def html(self):
return self.__html
def __build_pattern(self, label, **kwargs):
pattern = "<{}.*?".format(label)
for attr, value in kwargs.items():
if attr == "_class":
attr = "class"
pattern+='{}="{}"'.format(attr, value)
pattern += ".*?>(.*?)</{}>".format(label)
return pattern
def find(self, label, **kwargs):
pattern = self.__build_pattern(label, **kwargs)
instances = []
for _ in re.findall(pattern, self.__html):
instances.append(HTMLParser.Label(label, _, **kwargs))
return instances
if __name__ == "__main__":
html = "<html><body><p class='article'>在线Python教程 " \
"<a href='www.chipscoco.com'>Python零基础入门指南</a></p>" \
"<div><p><a href=\"www.chipscoco.com\">与薯条老师一起学Python</a></p>" \
"</div></body></html>"
html_parser = HTMLParser(html)
labels = html_parser.find("p")
for label in labels:
print(label.get_text())
labels = html_parser.find("a", href="www.chipscoco.com")
for label in labels:
print(label["href"], label["text"])- 彻底掌握Python中的网络编程
- 已经是最后一篇了
