爬虫代码写好了 运行 报错 怎么解决(语言-python|开发工具-pycharm)

Question

问题遇到的现象和发生背景

问题相关代码，请勿粘贴截图

# coding=gbk
import requests
from bs4 import BeautifulSoup
import os
import urllib.request

headers = {'user-agent': 'Mozilla/5.0'}
root_url = 'http://www.shuomingshuku.com/file/'
def getall():
    mkdir("D:\\Python爬取的文件\\")
    for i in range(1, 200, 1):
        _file = getHtml(i)
        getFile(_file)
def getHtml(page_id):
    testurl = str(root_url) + str(page_id)
    res = requests.get(testurl, headers=headers)
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")
    element_h1 = soup.find_all("h1")
    element_a = soup.find_all("a", attrs={"class": "btn", "rel": "nofollow"})
    file_name = element_h1[0].next
    file_url = element_a[0].attrs['href']
    return [file_name, file_url]
def getFile(files):
    file_name = files[0]
    u = urllib.request.urlopen(files[1])
    f = open("D:\\Python爬取的文件\\" + file_name + ".pdf", 'wb')
    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break

        f.write(buffer)
    f.close()
    print("成功-下载文件：" + file_name)
def mkdir(path):
    path = path.strip()
    path = path.rstrip("\\")
    isExists = os.path.exists(path)
    if not isExists:
        os.makedirs(path)
        return True
    else:
        return False
if __name__ == "__main__":
    getall()

运行结果及报错内容

"I:\Program Files\Python\python.exe" "I:/Program Files/Python/xuexi/xuexi02.py"
Traceback (most recent call last):
  File "I:\Program Files\Python\xuexi\xuexi02.py", line 47, in <module>
    getall()
  File "I:\Program Files\Python\xuexi\xuexi02.py", line 12, in getall
    _file = getHtml(i)
  File "I:\Program Files\Python\xuexi\xuexi02.py", line 22, in getHtml
    file_url = element_a[0].attrs['href']
IndexError: list index out of range

我想要达到的结果

Answer 1

把404排除掉的逻辑，你忘记加了，望采纳

# coding=gbk
import requests
from bs4 import BeautifulSoup
import os
import urllib.request

headers = {'user-agent': 'Mozilla/5.0'}
root_url = 'http://www.shuomingshuku.com/file/'


def getall():
    mkdir("D:\\Python爬取的文件\\")
    for i in range(1, 200, 1):
        _file = getHtml(i)
        if _file:
            getFile(_file)


def getHtml(page_id):
    testurl = str(root_url) + str(page_id)
    res = requests.get(testurl, headers=headers)
    if res.status_code == 404:
        print("\n当前page_id：" + str(page_id) + " 返回404")
        return None
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")
    element_h1 = soup.find_all("h1")
    element_a = soup.find_all("a", attrs={"class": "btn", "rel": "nofollow"})
    file_name = element_h1[0].next
    file_url = element_a[0].attrs['href']
    return [file_name, file_url]


def getFile(files):
    file_name = files[0]
    u = urllib.request.urlopen(files[1])
    f = open("D:\\Python爬取的文件\\" + file_name + ".pdf", 'wb')
    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break
        f.write(buffer)
    f.close()
    print("成功-下载文件：" + file_name)


def mkdir(path):
    path = path.strip()
    path = path.rstrip("\\")
    isExists = os.path.exists(path)
    if not isExists:
        os.makedirs(path)
        return True
    else:
        return False


if __name__ == "__main__":
    getall()