DSSIMP 发表于 2021-2-3 17:03:37

极客Python爬起豆瓣出现list index out of range错误怎么办

代码基本上照抄的小甲鱼的。最后运行出现list index out of range错误怎么解决啊{:10_266:}
有没有大佬有现在可运行的完整代码发一下啊

import requests
import bs4
import re

def open_url(url):
      headers={'user-agent':'Mozilla/5.0'}
      res=requests.get(url,headers=headers)
      return res

def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")

    movies=[]
    targets=soup.find_all("div",class_="hd")
    for each in targets:
      movies.append(each.a.span.text)

    ranks=[]
    targets=soup.find_all("span",class_="rating_num")
    for each in targets:
      ranks.append(' 评分：%s ' % each.text)

    messages=[]
    targets=soup.find_all("div",class_="bd")
    for each in targets:
      try:
            messages.append(each.p.text.split("\n"),strip()+each.p.text.split("\n").strip())
      except:
            continue

    result=[]
    length=len(movies)
    for i in range(length):
      result.append(movies+ranks+messages+"\n")

    return result

def find_depth(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")
    depth=soup.find("span",class_="next").previous_sibling.previous_sibling.text

    return int(depth)

def main():
    host="https://movie.douban.com/top250"
    res=open_url(host)
    depth=find_depth(res)

    result=[]
    for i in range(depth):
      url=host+"/?start=" + str(25 * i)
      res=open_url(url)
      result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
      for each in result:
            f.write(each)

if __name__=="__main__":
    main()

°蓝鲤歌蓝 发表于 2021-2-3 17:26:47

headers={'user-agent':'Mozilla/5.0'}
这个写错了

YunGuo 发表于 2021-2-3 18:38:24

代码第27句。写错了。
这一句。messages.append(each.p.text.split("\n")后面是'.strip()'，写成了逗号
messages.append(each.p.text.split("\n"),strip()+each.p.text.split("\n").strip())

DSSIMP 发表于 2021-2-3 19:14:48

°蓝鲤歌蓝 发表于 2021-2-3 17:26
这个写错了

{:10_266:}好的 已修改，但运行没反应{:10_245:}

DSSIMP 发表于 2021-2-3 19:15:18

YunGuo 发表于 2021-2-3 18:38
代码第27句。写错了。
这一句。messages.append(each.p.text.split("\n")后面是'.strip()'，写成了逗号 ...

感谢，已修改，但运行没反应{:10_266:}

°蓝鲤歌蓝 发表于 2021-2-3 19:16:15

报错信息贴出来

DSSIMP 发表于 2021-2-3 19:19:31

修改后的代码
原先有部分手打的出错了{:5_100:}
现在应该跟小甲鱼的一样了
但运行是没反应。。。。{:10_266:}
import requests
import bs4
import re

def open_url(url):
      headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
      res=requests.get(url,headers=headers)
      return res

def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")

    movies=[]
    targets=soup.find_all("div",class_="hd")
    for each in targets:
      movies.append(each.a.span.text)

    ranks=[]
    targets=soup.find_all("span",class_="rating_num")
    for each in targets:
      ranks.append(' 评分：%s ' % each.text)

    messages=[]
    targets=soup.find_all("div",class_="bd")
    for each in targets:
      try:
            messages.append(each.p.text.split("\n").strip()+each.p.text.split("\n").strip())
      except:
            continue

    result=[]
    length=len(movies)
    for i in range(length):
      result.append(movies+ranks+messages+"\n")
    return result

def find_depth(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")
    depth=soup.find("span",class_="next").previous_sibling.previous_sibling.text

    return int(depth)

def main():
    host="https://movie.douban.com/top250"
    res=open_url(host)
    depth=find_depth(res)

    result=[]
    for i in range(depth):
      url=host+"/?start=" + str(25 * i)
      res=open_url(url)
      result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
      for each in result:
            f.write(each)

if __name__=="__main__":
    main()

DSSIMP 发表于 2021-2-3 19:20:13

°蓝鲤歌蓝 发表于 2021-2-3 19:16
报错信息贴出来

不报错就是没反应了{:10_266:}

Daniel_Zhang 发表于 2021-2-3 19:22:13

没反应要么就是没有爬到东西，要么就是你没看到那个生成的文件

你挨个 print 一下，找找问题呗

能 print 的都 print 一下{:10_245:}

DSSIMP 发表于 2021-2-3 19:23:17

Daniel_Zhang 发表于 2021-2-3 19:22
没反应要么就是没有爬到东西，要么就是你没看到那个生成的文件

你挨个 print 一下，找找问题呗


{:10_266:}

DSSIMP 发表于 2021-2-3 19:59:46

爬虫成功了 感谢大家 {:5_106:}

手里尖刀刺 发表于 2021-8-20 09:55:23

DSSIMP 发表于 2021-2-3 19:59
爬虫成功了 感谢大家

能不能分享下完全体的代码呀小白路过 还在基础语法趴着 好难

DSSIMP 发表于 2021-8-20 14:04:38

手里尖刀刺 发表于 2021-8-20 09:55
能不能分享下完全体的代码呀小白路过 还在基础语法趴着 好难

import requests
import bs4
import re

def open_url(url):
      headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
      res=requests.get(url,headers=headers)
      return res

def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")

    movies=[]
    targets=soup.find_all("div",class_="hd")
    for each in targets:
      movies.append(each.a.span.text)

    ranks=[]
    targets=soup.find_all("span",class_="rating_num")
    for each in targets:
      ranks.append(' 评分：%s ' % each.text)

    messages=[]
    targets=soup.find_all("div",class_="bd")
    for each in targets:
      try:
            messages.append(each.p.text.split("\n").strip()+each.p.text.split("\n").strip())
      except:
            continue

    n=len(messages)
    for i in range(n):
      messages=messages.replace("\xa0"," ")

    result=[]
    length=len(movies)
    for i in range(length):
      result.append(movies+ranks+messages.replace("\xa0"," ")+"\n")
    return result

def find_depth(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")
    depth=soup.find("span",class_="next").previous_sibling.previous_sibling.text

    return int(depth)

def main():
    host="https://movie.douban.com/top250"
    res=open_url(host)
    depth=find_depth(res)

    result=[]
    for i in range(depth):
      url=host+"/?start=" + str(25 * i)
      res=open_url(url)
      result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
      for each in result:
            f.write(each)

if __name__=="__main__":
    main()

DSSIMP 发表于 2021-8-20 14:05:44

DSSIMP 发表于 2021-8-20 14:04
import requests
import bs4
import re


import requests
import bs4
import re

def open_url(url):
      headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
      res=requests.get(url,headers=headers)
      return res

def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")

    movies=[]
    targets=soup.find_all("div",class_="hd")
    for each in targets:
      movies.append(each.a.span.text)

    ranks=[]
    targets=soup.find_all("span",class_="rating_num")
    for each in targets:
      ranks.append(' 评分：%s ' % each.text)

    messages=[]
    targets=soup.find_all("div",class_="bd")
    for each in targets:
      try:
            messages.append(each.p.text.split("\n").strip()+each.p.text.split("\n").strip())
      except:
            continue

    n=len(messages)
    for i in range(n):
      messages=messages.replace("\xa0"," ")

    result=[]
    length=len(movies)
    for i in range(length):
      result.append(movies+ranks+messages.replace("\xa0"," ")+"\n")
    return result

def find_depth(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")
    depth=soup.find("span",class_="next").previous_sibling.previous_sibling.text

    return int(depth)

def main():
    host="https://movie.douban.com/top250"
    res=open_url(host)
    depth=find_depth(res)

    result=[]
    for i in range(depth):
      url=host+"/?start=" + str(25 * i)
      res=open_url(url)
      result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
      for each in result:
            f.write(each)

if __name__=="__main__":
    main()

DSSIMP 发表于 2021-8-20 14:07:22

手里尖刀刺 发表于 2021-8-20 09:55
能不能分享下完全体的代码呀小白路过 还在基础语法趴着 好难

import requests
import bs4
import re

def open_url(url):
      headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
      res=requests.get(url,headers=headers)
      return res

def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")

    movies=[]
    targets=soup.find_all("div",class_="hd")
    for each in targets:
      movies.append(each.a.span.text)

    ranks=[]
    targets=soup.find_all("span",class_="rating_num")
    for each in targets:
      ranks.append(' 评分：%s ' % each.text)

    messages=[]
    targets=soup.find_all("div",class_="bd")
    for each in targets:
      try:
            messages.append(each.p.text.split("\n").strip()+each.p.text.split("\n").strip())
      except:
            continue

    n=len(messages)
    for i in range(n):
      messages=messages.replace("\xa0"," ")

    result=[]
    length=len(movies)
    for i in range(length):
      result.append(movies+ranks+messages.replace("\xa0"," ")+"\n")
    return result

def find_depth(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")
    depth=soup.find("span",class_="next").previous_sibling.previous_sibling.text

    return int(depth)

def main():
    host="https://movie.douban.com/top250"
    res=open_url(host)
    depth=find_depth(res)

    result=[]
    for i in range(depth):
      url=host+"/?start=" + str(25 * i)
      res=open_url(url)
      result.extend(find_movies(res))

    with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
      for each in result:
            f.write(each)

if __name__=="__main__":
    main()

手里尖刀刺 发表于 2021-8-20 16:14:07

C:\Users\gt20180105\Desktop这是什么情况啊 请求无效

ITxiong 发表于 2022-1-2 16:38:55

手里尖刀刺 发表于 2021-8-20 16:14
这是什么情况啊 请求无效

你没有下载预先下载好requests，先用pip指令下载
页: [1]
查看完整版本: 极客Python爬起豆瓣出现list index out of range错误怎么办