汤圆创作小说检索信息采集

# -*- coding: utf-8 -*-
"""
-------------------------------------------------
@ Author ：Lan
@ Blog ：www.lanol.cn
@ Date ： 2020/9/30
@ Description：I'm in charge of my Code
-------------------------------------------------
"""
import requests
import parsel

for i in range(1, 10094):
    url = f'https://www.itangyuan.com/search/book/%E4%B8%80%20%E7%94%9F.html?page={i}'
    res = requests.get(url).text
    xpathFile = parsel.Selector(res)
    author = xpathFile.xpath("//p[@class='author']/a/text()").extract()
    name = xpathFile.xpath("//p[@class='bname']/a/text()").extract()
    info = xpathFile.xpath("//p[@class='rw_info']/text()").extract()
    for index, value in enumerate(name):
        if '一' in value.replace(' ', '') and '生' in value.replace(' ', ''):
            if int(info[index].split('阅读')[0].replace(' ', '')) < 1000:
                print(value, author[index], info[index].split('/')[-1])
    print(f'已检测至第{i}页')