娉ㄦ剰锛氭垜浠钩鏃惰闂槸鐢ㄦ祻瑙堝櫒璁块棶锛屼絾鏄敱浜庢垜浠紪鍐欎唬鐮侊紝鍒╃敤python锛屼负浜嗚缃戠珯璁や负鎴戜滑鐨勮闂睘浜庢甯哥敤鎴疯涓哄拰鑼冨洿锛屼负浜嗘墦鍏ュ唴閮紝鎴戜滑鍙兘浼鑷繁銆傜幇鍦ㄥ幓浼锛?]/p

鑾峰彇title淇℃伅锛?/p>

//h1/test锛堬級

鍒版鍩烘湰鎼炲畾锛屽皾璇曟墦鍗扮粨鏋溿€?/p>

print(info)
 print(title)

杩欐槸鎴戜滑鍙戠幇涓€鍫嗗唴瀹癸紝鍥犱负娌℃湁鏄剧ず鏂囨湰鍐呭銆?]/p/text()

涔嬪悗淇濆瓨鏂囦欢銆傚嵆鍙疄鐜拌繍琛屻€?瀹屾暣浠ｇ爜濡備笅锛?/p>

# 鎬庝箞鍙戦€佽姹?/span>
# pip install requests
import requests
# pip install lxml
from lxml import etree
# 鍙戦€佺粰璋?/span>
url = 'https://www.93xscc.com/9034/2126907.html'
while True:
    # 浼鑷繁
   headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 Edg/109.0.1518.52'
}

    # 鍙戦€佽姹?/span>
    resp = requests.get(url,headers=headers)
    # 璁剧疆缂栫爜
    resp.encoding = 'utf-8'
    # 鍝嶅簲淇℃伅
    # print(resp.text)
    e = etree.HTML(resp.text)
    info = '\n'.join(e.xpath('//div[@]/p/text()'))
    title = e.xpath('//h1/text()')[0]
    url = f'https://www.85xs.cc{e.xpath("//tr/td[2]/a/@href")[0]}'
    # print(info)
    # print(title)
    # 淇濆瓨
    with open('鏂楃綏澶ч檰.txt','w',encoding='utf-8') as f:
        f.write(title+'\n\n'+info+'\n\n')

    '''
    閫€鍑哄惊鐜?break
    if url == '/book/douluodalu1/'
    '''