Python爬虫问题

问题遇到的现象和发生背景

#爬虫的代码，在143,40,91分别出现了错误。

C:\Users\Administrator\PycharmProjects\pythonProject4\demo3day3\venv\Scripts\python.exe C:/Users/Administrator/PycharmProjects/pythonProject4/douban/spider.py
Traceback (most recent call last):
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 143, in 
    main()
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 40, in main
    datalist = getData(baseurl)
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 91, in getData
    data.append(titles[0])
IndexError: list index out of range

Process finished with exit code 1

用代码块功能插入代码，请勿粘贴截图

# -*- codeing = utf-8 -*-
# @Time : 2022/9/11 0011 16:51
# @Author : Madara
# @File : spider.py
# @Software: PyCharm

# def main():     #ctrl+/注释多行
#     print("hello")
# main()
#
# if __name__ == "__main__":    #当程序执行时
#     #调用函数
#     main()


# def main(a):
#     print("hello",a)
# main(1)
#
# if __name__ == "__main__":    #当程序执行时。主程序执行的入口，开始阶段
#     #调用函数
#     main(2)

import urllib.parse as urillib
import urllib.request as urllib2
import sys
import os
import urllib.request
import bs4  #网页解析，获取数据
import sqlite3  #进行SQLite数据库操作
import re #正则表达式，进行文字匹配
import urllib  #指定URL，获取网页数据
import xlwt #进行Excel操作
from bs4 import BeautifulSoup


def main():
    baseurl = "https://movie.douban.com/top250?start="
    #1.爬取网页
    datalist = getData(baseurl)
    savepath = ".\\豆瓣电影Top250.xls"    #./保存在当前文件夹，.\\保存在文件
 #3.保存数据
    #saveData(savepath)
   #askURL("https://movie.douban.com/top250?start=0")

#影片详情链接的规则
# findLink = re.compile(r'  ') #创建正则表达式对象，表示规则（字符串的模式）
#影片图片的链接
findImgSrc = re.compile(r', re.S)  #re.S让换行符包含在字符中
#影片片名
findTitle = re.compile(r' (.*)  ')
#影片评分
findRating = re.compile(r' (.*) ')
#评价人数
findJudge = re.compile(r' (\d*)人评价 ')
#找到概况
findInq = re.compile(r' (.*) ')
#找到影片的相关内容
findBd = re.compile(r' 
(.*?)
, re.S ')



#爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,10):     #左闭右开.  调用获取页面信息的函数，10次。
        url = baseurl + str(i * 25)
        html = askURL(url)   #保存获取到的网页源码



        #2.逐一解析数据
        soup = BeautifulSoup(html, "html.parser")
        for item in soup.find_all("div", class_="item"):    #查找符合要求的字符串，形成列表。class要加下划线。
            #print(item)  #测试，查看电影item全部信息
            data = []    #保存一部电影的所有信息
            item = str(item)

            #获取到影片的超链接，影片详情的链接
            # link = re.findall(findLink,item)[0] #re库通过正则表达式来查找指定的字符串
            # print(link)                       #添加链接
            imgSrc = re.findall(findImgSrc,item)[0] #添加图片
            data.append(imgSrc)
            titles = re.findall(findTitle,item)     #片名可能只有一个中文名，没有外文名
            if len(titles) == 2:
                ctitle = titles[0]    #添加中文名
                data.append(ctitle)
                otitle = titles[1].replace("/","")  #去掉无关的符号
                data.append(otitle)    #添加外国名
            else:
                data.append(titles[0])
                data.append('   ')     #外国名留空。每一行每一列也要占位置
            rating =re.findall(findRating,item)[0]
            data.append(rating)           #添加评分

            judgeNum = re.findall(findJudge,item)[0]
            data.append(judgeNum)       #添加评价人数

            inq = re.findall(findInq,item)
            if len(inq) != 0:
                inq = inq[0].replace("。", "")  #去掉句号
                data.append(inq)  # 添加概述
            else:
                data.append(" ")     #留空
            bd = re.findall(findBd,item)[0]
            bd = re.sub( ' (\s+)?', " ", bd)   #去掉
，三个位置，第一个是标准，第二是替换的字符，第三个要操作的字符串
            bd = re.sub('/'," ", bd)  #替换/
            data.append(bd.strip())      #去掉前后的空格

            datalist.append(data)         #把处理好的一部电影信息放入datalist

    #print(datalist)
    return datalist


#得到指定一个URL的网页内容
def askURL(url):
    head = {                  #模拟浏览器头部信息，向豆瓣服务器发送消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 105.0.0.0Safari / 537.36"
    }                      #User-Agent很重要，要保证大小写，而且不能有空格，与网页端保持一致
                    #用户代理，表示告诉豆瓣服务器，我们是什么类型的机器，浏览器（本质上是告诉浏览器我们可以接收什么水平的文件内容）
    request = urllib.request.Request(url, headers = head)
    html = " "
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
       #print(html)
    except urllib.error.URLerror as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)

    return html



#3.保存数据
def saveData(savepath):
    print("save...")

if __name__ == "__main__":
    main()

C:\Users\Administrator\PycharmProjects\pythonProject4\demo3day3\venv\Scripts\python.exe C:/Users/Administrator/PycharmProjects/pythonProject4/douban/spider.py
Traceback (most recent call last):
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 143, in 
    main()
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 40, in main
    datalist = getData(baseurl)
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 91, in getData
    data.append(titles[0])
IndexError: list index out of range

Process finished with exit code 1C:\Users\Administrator\PycharmProjects\pythonProject4\demo3day3\venv\Scripts\python.exe C:/Users/Administrator/PycharmProjects/pythonProject4/douban/spider.py
Traceback (most recent call last):
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 143, in 
    main()
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 40, in main
    datalist = getData(baseurl)
  File "C:\Users\Administrator\PycharmProjects\pythonProject4\douban\spider.py", line 91, in getData
    data.append(titles[0])
IndexError: list index out of range

Process finished with exit code 1

检查一下titles这个列表是不是空的叭，根据报错信息来看的话应该是因为它是空的

title 是个空列表，所以空列表取0报错，可以取值之前先做一次判断，如果不为空再取值