28 lines
868 B
Python
28 lines
868 B
Python
from pageextractor.PageExtractor import PageExtractor
|
|
|
|
|
|
class ZhonghuaExtractor(PageExtractor):
|
|
def get_title(self) -> str:
|
|
if self._soup is None:
|
|
return ""
|
|
t = self._soup.select_one("h1.article_title")
|
|
return t.text.strip() if t is not None else ""
|
|
|
|
def get_source(self) -> str:
|
|
if self._soup is None:
|
|
return ""
|
|
t = self._soup.select_one("span.source")
|
|
return t.text.strip() if t is not None else ""
|
|
|
|
def get_time(self) -> str:
|
|
if self._soup is None:
|
|
return ""
|
|
t = self._soup.select_one("span.time")
|
|
return t.text.strip() if t is not None else ""
|
|
|
|
def get_content(self) -> str:
|
|
if self._soup is None:
|
|
return ""
|
|
t = self._soup.select_one("#js_article_content")
|
|
return t.text.strip() if t is not None else ""
|