这个代码为什么输出出来只有一条数据的？

Question

-*- coding: utf-8 -*-

"""
Created on Tue Oct 27 19:25:44 2020

@author: lenovo
"""

import requests
from bs4 import BeautifulSoup
import time

headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3823.400 QQBrowser/10.6.4302.400'
}

def get_info(url):
wb_data = requests.get(url,headers = headers)
soup = BeautifulSoup(wb_data.text,'lxml')

ranks = soup.select('#rankWrap > div.pc_temp_songlist > ul > li:nth-child(1) > span.pc_temp_num > strong')
tittles = soup.select('#rankWrap > div.pc_temp_songlist > ul > li:nth-child(1) > a')
times = soup.select('#rankWrap > div.pc_temp_songlist > ul > li:nth-child(1) > span.pc_temp_tips_r > span')

for rank,tittle,time in zip(ranks,tittles,times):
    data = {
        'rank':rank.get_text().strip(),
        'singer':tittle.get_text().split('-')[0],
        'song':tittle.get_text().split('-')[1],

        'time':time.get_text().strip()
        }
    print(data)

if name == '__main__':
urls = ['https://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range (1,24)]
for url in urls:
get_info(url)

time.sleep(1)


![图片说明](https://img-ask.csdn.net/upload/202010/27/1603800054_296603.png)

Answer 1

由于本人bs4库用的不是很熟，我爬虫习惯用 etree，所以我把你的代码用lxml库完善了下

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import requests
from lxml import etree

headers = {
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3823.400 QQBrowser/10.6.4302.400'
}

def get_info(url):
    wb_data = requests.get(url,headers = headers)
    html = etree.HTML(wb_data.content.decode('utf-8'))
    songs_list = html.xpath('//div[@id="rankWrap"]//div[@class="pc_temp_songlist "]/ul/li')

    for item in songs_list:
        title = item.xpath('./@title')[0]
        try:
            rank = item.xpath('.//span[@class="pc_temp_num"]/strong/text()')[0].strip()
        except Exception:
            rank = item.xpath('.//span[@class="pc_temp_num"]/text()')[0].strip()

        singer, song = title.split(' - ')
        time_song = item.xpath('.//span[@class="pc_temp_tips_r"]//span[@class="pc_temp_time"]/text()')[0]
        data = {
            "rank": rank,
            "singer": singer.strip(),
            "song": song.strip(),
            "time": time_song.strip()
        }
        print(data)

if __name__ == '__main__':
    urls = ['https://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range (1,24)]
    for url in urls:
        get_info(url)