百度api搜索，跳过安全验证

如果没记错，需要安装东西，引擎啥的

import time
from selenium import webdriver
from selenium.webdriver import ChromeOptions
from selenium.webdriver.common.by import By
from urllib.parse import urlencode

def get_url(keywords: list):
    keyword = " ".join(keywords)
    q1 = {"q1": keyword}
    q1 = urlencode(q1)
    url = f"https://www.baidu.com/s?{q1}&q2=&q3=&q4=&gpc=stf&ft=&q5=&q6=www.szgm.gov.cn&tn=baiduadv&ie=utf-8"
    return url

# {text:url, }
def get_herf_text(url) -> dict:
    option = ChromeOptions() # 隐藏webdriver提示条&自动化扩展信息，跳过验证
    option.add_experimental_option('excludeSwitches',['enable-automation'])
    option.add_experimental_option('useAutomationExtension',False)

    # 无头模式访问
    option.add_argument("--headless")
    option.add_argument("--disable-gpu")
    option.add_argument("--no-sandbox")

    br = webdriver.Chrome(options = option)
    br.execute_cdp_cmd(
        "Page.addScriptToEvaluateOnNewDocument",
        {'source':'Object.defineProperty(navigator,"webdriver",{get:()=>undefined})'})
    br.get(url)
    links = br.find_elements(By.XPATH,"//h3[@class='c-title t t tts-title']/a[contains(normalize-space(@class), '')]")
    # 遍历每个链接元素，获取 href 和文本内容
    result = {}
    for link in links:
        href = link.get_attribute("href")
        text = link.text
        result[text] = href
    return result

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