Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix baidusearch and duckduckgosearch #1488

Merged
merged 2 commits into from
Jul 12, 2024
Merged

Fix baidusearch and duckduckgosearch #1488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
de2e7c9
Update baidu.py
guoyuhao2330 Jul 12, 2024
8b35243
Update duckduckgosearch.py
guoyuhao2330 Jul 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions graph/component/baidu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,10 +53,11 @@ def _run(self, history, **kwargs):
url_res = re.findall(r"'url': \\\"(.*?)\\\"}", response.text)
title_res = re.findall(r"'title': \\\"(.*?)\\\",\\n", response.text)
body_res = re.findall(r"\"contentText\":\"(.*?)\"", response.text)
baidu_res = [re.sub('<em>|</em>', '', '<a href="' + url + '">' + title + '</a> ' + body) for url, title, body
in zip(url_res, title_res, body_res)]
baidu_res = [{"content": re.sub('<em>|</em>', '', '<a href="' + url + '">' + title + '</a> ' + body)} for url, title, body in zip(url_res, title_res, body_res)]
del body_res, url_res, title_res

print(baidu_res, ":::::::::::::::::::::::::::::::::")
return Baidu.be_output(baidu_res)
df = pd.DataFrame(baidu_res)
print(df, ":::::::::::::::::::::::::::::::::")

return df

11 changes: 6 additions & 5 deletions graph/component/duckduckgosearch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,18 +44,19 @@ def _run(self, history, **kwargs):
ans = self.get_input()
ans = " - ".join(ans["content"]) if "content" in ans else ""
if not ans:
return Baidu.be_output(self._param.no)
return DuckDuckGoSearch.be_output(self._param.no)

if self.channel == "text":
with DDGS() as ddgs:
# {'title': '', 'href': '', 'body': ''}
duck_res = ['<a href="' + i["href"] + '">' + i["title"] + '</a> ' + i["body"] for i in
duck_res = [{"content": '<a href="' + i["href"] + '">' + i["title"] + '</a> ' + i["body"]} for i in
ddgs.text(ans, max_results=self._param.top_n)]
elif self.channel == "news":
with DDGS() as ddgs:
# {'date': '', 'title': '', 'body': '', 'url': '', 'image': '', 'source': ''}
duck_res = ['<a href="' + i["url"] + '">' + i["title"] + '</a> ' + i["body"] for i in
duck_res = [{"content": '<a href="' + i["url"] + '">' + i["title"] + '</a> ' + i["body"]} for i in
ddgs.news(ans, max_results=self._param.top_n)]

print(duck_res, ":::::::::::::::::::::::::::::::::")
return DuckDuckGoSearch.be_output(duck_res)
df = pd.DataFrame(duck_res)
print(df, ":::::::::::::::::::::::::::::::::")
return df