File size: 2,244 Bytes
d9499f9 f3a1380 fd69a6c f3a1380 d9499f9 fd69a6c 230447c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import random
from abc import ABC
from functools import partial
import pandas as pd
import requests
import re
from graph.component.base import ComponentBase, ComponentParamBase
class BaiduParam(ComponentParamBase):
"""
Define the Baidu component parameters.
"""
def __init__(self):
super().__init__()
self.top_n = 10
def check(self):
self.check_positive_integer(self.top_n, "Top N")
class Baidu(ComponentBase, ABC):
component_name = "Baidu"
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)
url = 'https://www.baidu.com/s?wd=' + ans + '&rn=' + str(self._param.top_n)
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'}
response = requests.get(url=url, headers=headers)
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 = [{"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
df = pd.DataFrame(baidu_res)
print(df, ":::::::::::::::::::::::::::::::::")
return df
|