爬虫爬取该网站时返回空列表

Question

import requests
from bs4 import BeautifulSoup
import csv

def getHtml(url):
    try:
        r=requests.get(url)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return "fail"
    
def getDATA(ulist,html):
    soup=BeautifulSoup(html,'html.parser')
    table=soup.find_all('tr')
    for row in table:
        cols=[col.text for col in row.find_all('td')]
        if len(cols)==0 or not cols[0].isdigit():
            continue
        ulist.append(cols)

def main():
    unifo=[]
    url='https://www.phb123.com/hangye/qiche/index_1.html'
    html=getHtml(url)
    getDATA(unifo,html)
    print(html)
    print('*'*20)
    print(unifo)
main()

有大佬能帮忙解决一下吗？

Answer 1

第一列不是包含了换行和空白，导致是否数字判断失败，要去掉空白就可以了，加下面加粗的内容，帮助到你可以点击采纳吗，谢谢~~

def getDATA(ulist,html):
    soup=BeautifulSoup(html,'html.parser')
    table=soup.find_all('tr')
    for row in table:
        cols=[col.text for col in row.find_all('td')]
        if len(cols)==0 or not cols[0].strip().isdigit():
           continue
        ulist.append(cols)