async def resolve_url_to_content(self, url):
if not url.startswith(self.url):
return None
art = url_to_n3karticle(url)
text = clean_html_text(art.text)
if len(text) < 100:
return None
return text
async def resolve_url_to_content(self, url):
if not url.startswith(self.url):
return None
art = url_to_n3karticle(url)
text = clean_html_text(art.text)
filtered_text = "\n".join([
line for line in text.split("\n") if not line.startswith("Photo:")
])
return filtered_text
async def resolve_url_to_content(self, url):
if not url.startswith(self.url):
return None
art = url_to_n3karticle(url)
text = clean_html_text(art.text)
filtered_text = "\n".join([
line for line in text.split("\n")
if not string_contains(line, IGNORE_ITEMS)
])
return filtered_text
async def resolve_url_to_content(self, url):
art = url_to_n3karticle(url)
text = clean_html_text(art.text)
if len(text) < 100:
return None
for trim_token in TRIM_AT:
try:
idx = text.index(trim_token)
except:
continue
text = text[:idx].strip()
return text
async def resolve_url_to_content(self, url):
html = await self._get(url.replace(self.url, ""))
art = url_to_n3karticle(url, input_html=html)
text = clean_html_text(art.text)
return text