代码拉取完成,页面将自动刷新
import requests
from lxml import etree
import 起点中文小说章节爬取 as my_func1
def get_book_url(book):
book_url = f'https://www.qidian.com/so/{book}.html'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.48',
}
try:
resp = requests.get(url=book_url, headers=headers)
resp.encoding = 'utf-8'
tree = etree.HTML(resp.text)
book_url = tree.xpath('//*[@id="result-list"]/div/ul/li[1]/div[2]/h3/a/@href')
return 'https:' + book_url[0]
except:
return ''
def input_name():
novel_name = input("请输入你想获取的书名\n>>>:")
return novel_name
def crawl_chapter(book_url):
my_func1.main(book_url)
def main():
novel_name = input_name()
book_url = get_book_url(novel_name)
crawl_chapter(book_url)
if __name__ == '__main__':
main()
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。