selenium必应搜索，获取标题以及url

必应搜索，获取标题以及url

import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException

import urllib.parse

def get_content(driver, url):
    driver.get(url)
    time.sleep(sleep_time)
    targets = driver.find_elements_by_xpath("//li[@class='b_algo']/h2/a")
    infos = []
    for t in targets:
        text = t.text
        href = t.get_attribute("href")
        url_parse = urllib.parse.urlparse(href)
        domain = url_parse.scheme + "://" + url_parse.netloc
        infos.append(text+"||"+domain+"||"+href+"\n")
    return infos


def main(key, page=2):
    driver = webdriver.Chrome('./driver/chromedriver.exe')
    driver.implicitly_wait(10)
    url = f"https://cn.bing.com/search?q={key}&qs=n&sp=-1&pq=ni&sc=8-2&sk=&cvid=51AA598AE26B4774B0C37C165EB69C9B&first=1&FORM=PQRE1&ensearch=1"

    result = []
    for i in range(page):
        result += get_content(driver, url)
        print(f"page {i} over")
        try:
            el_next_page = driver.find_element_by_xpath("//a[@title='Next page']")
            url = el_next_page.get_attribute("href")
        except NoSuchElementException:
            break

    driver.quit()

    with open(f"result{time.strftime('%H %M %S')}.txt", 'w', encoding='utf-8') as f:
        f.writelines(result)


if __name__ == '__main__':
    sleep_time = 1
    main("123", page=2)