28 lines
876 B
Python
28 lines
876 B
Python
from pageextractor.PageExtractor import PageExtractor
|
|
|
|
|
|
class YouthExtractor(PageExtractor):
|
|
def get_title(self) -> str:
|
|
if self._soup is None:
|
|
return ""
|
|
t = self._soup.select_one("div.page_title>h1")
|
|
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("#source_baidu")
|
|
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("#page_right")
|
|
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("div.page_left>div.page_k2")
|
|
return t.text.strip() if t is not None else ""
|