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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Baidu_
.. _Baidu: https://www.baidu.com
"""
# There exits a https://github.com/ohblue/baidu-serp-api/
# but we don't use it here (may we can learn from).
from urllib.parse import urlencode
from datetime import datetime
from html import unescape
import time
import json
from searx.exceptions import SearxEngineAPIException
from searx.utils import html_to_text
about = {
"website": "https://www.baidu.com",
"wikidata_id": "Q14772",
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
"language": "zh",
}
paging = True
categories = []
results_per_page = 10
baidu_category = 'general'
time_range_support = True
time_range_dict = {"day": 86400, "week": 604800, "month": 2592000, "year": 31536000}
def init(_):
if baidu_category not in ('general', 'images', 'it'):
raise SearxEngineAPIException(f"Unsupported category: {baidu_category}")
def request(query, params):
page_num = params["pageno"]
category_config = {
'general': {
'endpoint': 'https://www.baidu.com/s',
'params': {
"wd": query,
"rn": results_per_page,
"pn": (page_num - 1) * results_per_page,
"tn": "json",
},
},
'images': {
'endpoint': 'https://image.baidu.com/search/acjson',
'params': {
"word": query,
"rn": results_per_page,
"pn": (page_num - 1) * results_per_page,
"tn": "resultjson_com",
},
},
'it': {
'endpoint': 'https://kaifa.baidu.com/rest/v1/search',
'params': {
"wd": query,
"pageSize": results_per_page,
"pageNum": page_num,
"paramList": f"page_num={page_num},page_size={results_per_page}",
"position": 0,
},
},
}
query_params = category_config[baidu_category]['params']
query_url = category_config[baidu_category]['endpoint']
if params.get("time_range") in time_range_dict:
now = int(time.time())
past = now - time_range_dict[params["time_range"]]
if baidu_category == 'general':
query_params["gpc"] = f"stf={past},{now}|stftype=1"
if baidu_category == 'it':
query_params["paramList"] += f",timestamp_range={past}-{now}"
params["url"] = f"{query_url}?{urlencode(query_params)}"
return params
def response(resp):
text = resp.text
if baidu_category == 'images':
# baidu's JSON encoder wrongly quotes / and ' characters by \\ and \'
text = text.replace(r"\/", "/").replace(r"\'", "'")
data = json.loads(text, strict=False)
parsers = {'general': parse_general, 'images': parse_images, 'it': parse_it}
return parsers[baidu_category](data)
def parse_general(data):
results = []
if not data.get("feed", {}).get("entry"):
raise SearxEngineAPIException("Invalid response")
for entry in data["feed"]["entry"]:
if not entry.get("title") or not entry.get("url"):
continue
published_date = None
if entry.get("time"):
try:
published_date = datetime.fromtimestamp(entry["time"])
except (ValueError, TypeError):
published_date = None
# title and content sometimes containing characters such as & ' " etc...
title = unescape(entry["title"])
content = unescape(entry.get("abs", ""))
results.append(
{
"title": title,
"url": entry["url"],
"content": content,
"publishedDate": published_date,
}
)
return results
def parse_images(data):
results = []
if "data" in data:
for item in data["data"]:
if not item:
# the last item in the JSON list is empty, the JSON string ends with "}, {}]"
continue
replace_url = item.get("replaceUrl", [{}])[0]
width = item.get("width")
height = item.get("height")
img_date = item.get("bdImgnewsDate")
publishedDate = None
if img_date:
publishedDate = datetime.strptime(img_date, "%Y-%m-%d %H:%M")
results.append(
{
"template": "images.html",
"url": replace_url.get("FromURL"),
"thumbnail_src": item.get("thumbURL"),
"img_src": replace_url.get("ObjURL"),
"title": html_to_text(item.get("fromPageTitle")),
"source": item.get("fromURLHost"),
"resolution": f"{width} x {height}",
"img_format": item.get("type"),
"filesize": item.get("filesize"),
"publishedDate": publishedDate,
}
)
return results
def parse_it(data):
results = []
if not data.get("data", {}).get("documents", {}).get("data"):
raise SearxEngineAPIException("Invalid response")
for entry in data["data"]["documents"]["data"]:
results.append(
{
'title': entry["techDocDigest"]["title"],
'url': entry["techDocDigest"]["url"],
'content': entry["techDocDigest"]["summary"],
}
)
return results
|
