爬取妹子图网站报错

小甲鱼_py

import requests
import os
import time
from bs4 import BeautifulSoup

def open_url(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36",
        "Referer": url
    }
    soup=requests.get(url,headers=headers)

    return soup

def get_list(soup):
    html=BeautifulSoup(soup.content, 'lxml')
    a_list=html.find_all("ul",attrs={'id':'pins'})[0].find_all('li')

    for each in a_list:
        href_list.append(each.find_all('span')[0].find_all('a')[0]['href'])
        alt_list.append(each.find_all('span')[0].find_all('a')[0].string)
    return (alt_list,href_list)


def img_save(img):
    name=img.split('/')[-1]
    with open(name,'wb') as f:
        f.write(open_url(img).content)

def make_dir(pwd):
    os.mkdir(pwd)
    print("创建文件夹："+pwd)
    os.chdir(pwd)

def get_img(each):
    i = 0
    while True:
        page_url = each + "//" + str(i)
        soup = open_url(page_url)
        img_url = BeautifulSoup(soup.content, 'lxml')
        img = img_url.find_all('div', attrs={'class': 'main-image'})[0].img['src']
        print("正在抓取图片：" + img)
        img_save(img)
        time.sleep(3)
        page = img_url.find_all('div', attrs={'class': 'pagenavi'})[0].find_all('span')[-2].string
        i = i + 1
        if i == 1:
            i = 2
        if i > int(page):
            break

href_list = []
alt_list = []
y=0
for i in range(7,8):
    h=open_url("https://www.mzitu.com/page/"+str(i))
    alt_list,h_list=get_list(h)

for each in h_list:
    make_dir(alt_list[y])
    y = y + 1
    get_img(each)
    os.chdir(r"C:\Users\jok\PycharmProjects\untitled")

爬取到一半时候会报这个错误：

Traceback (most recent call last):
  File "C:/Users/jok/PycharmProjects/untitled/pange.py", line 62, in <module>
    get_img(each)
  File "C:/Users/jok/PycharmProjects/untitled/pange.py", line 41, in get_img
    img = img_url.find_all('div', attrs={'class': 'main-image'})[0].img['src']
IndexError: list index out of range

Stubborn

1. img = img_url.find_all('div', attrs={'class': 'main-image'})[0].img['src']

复制代码

IndexError: list index out of range  

表示超出索引，可能是没有采集到信息，页面可能不一样，加try  抓什么（url）页面报错，分析一下原因

wongyusing

你以年份区分一下图片的链接就能得到答案了