File size: 4,365 Bytes
138c09e
 
 
 
 
 
 
 
 
 
 
 
 
 
4d3e890
138c09e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4d3e890
 
 
 
138c09e
 
 
 
 
 
4d3e890
 
138c09e
 
 
 
 
 
 
4d3e890
 
 
 
 
 
 
 
 
 
 
 
138c09e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
import argparse
import os
import sys
import uvicorn

from fastapi import FastAPI, Depends
from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
from pydantic import BaseModel, Field
from typing import Union
from sse_starlette.sse import EventSourceResponse, ServerSentEvent
from utils.logger import logger
from networks.google_searcher import GoogleSearcher
from networks.html_fetcher import HTMLFetcher
from documents.query_results_extractor import QueryResultsExtractor
from documents.webpage_content_extractor import WebpageContentExtractor
from utils.logger import logger


class SearchAPIApp:
    def __init__(self):
        self.app = FastAPI(
            docs_url="/",
            title="Web Search API",
            swagger_ui_parameters={"defaultModelsExpandDepth": -1},
            version="1.0",
        )
        self.setup_routes()

    class QueriesToSearchResultsPostItem(BaseModel):
        queries: list = Field(
            default=[""],
            description="(list[str]) Queries to search",
        )
        result_num: int = Field(
            default=10,
            description="(int) Number of search results",
        )
        safe: bool = Field(
            default=False,
            description="(bool) Enable SafeSearch",
        )
        types: list = Field(
            default=["web"],
            description="(list[str]) Types of search results: `web`, `image`, `videos`, `news`",
        )
        extract_content: bool = Field(
            default=False,
            description="(bool) Enable extracting main text contents from webpage, will add `text` filed in each `query_result` dict",
        )

    def queries_to_search_results(self, item: QueriesToSearchResultsPostItem):
        google_searcher = GoogleSearcher()
        query_results_extractor = QueryResultsExtractor()
        queries_search_results = []
        for query in item.queries:
            if not query.strip():
                continue
            query_html_path = google_searcher.search(
                query=query, result_num=item.result_num, safe=item.safe
            )
            query_search_results = query_results_extractor.extract(query_html_path)
            queries_search_results.append(query_search_results)
        logger.note(queries_search_results)

        if item.extract_content:
            html_fetcher = HTMLFetcher()
            webpage_content_extractor = WebpageContentExtractor()
            for query_idx, query_search_result in enumerate(queries_search_results):
                for query_result_idx, query_result in enumerate(
                    query_search_result["query_results"]
                ):
                    html_path = html_fetcher.fetch(query_result["url"])
                    extracted_content = webpage_content_extractor.extract(html_path)
                    queries_search_results[query_idx]["query_results"][
                        query_result_idx
                    ]["text"] = extracted_content
        return queries_search_results

    def setup_routes(self):
        self.app.post(
            "/queries_to_search_results",
            summary="Search queries, and extract contents from results",
        )(self.queries_to_search_results)


class ArgParser(argparse.ArgumentParser):
    def __init__(self, *args, **kwargs):
        super(ArgParser, self).__init__(*args, **kwargs)

        self.add_argument(
            "-s",
            "--server",
            type=str,
            default="0.0.0.0",
            help="Server IP for Web Search API",
        )
        self.add_argument(
            "-p",
            "--port",
            type=int,
            default=21111,
            help="Server Port for Web Search API",
        )

        self.add_argument(
            "-d",
            "--dev",
            default=False,
            action="store_true",
            help="Run in dev mode",
        )

        self.args = self.parse_args(sys.argv[1:])


app = SearchAPIApp().app

if __name__ == "__main__":
    args = ArgParser().args
    if args.dev:
        uvicorn.run("__main__:app", host=args.server, port=args.port, reload=True)
    else:
        uvicorn.run("__main__:app", host=args.server, port=args.port, reload=False)

    # python -m apis.search_api      # [Docker] in product mode
    # python -m apis.search_api -d   # [Dev]    in develop mode