关于小甲鱼办公篇第一个案例
我一步一步跟的，结果报错了，大哥大姐们求解，爱你们(づ￣3￣)づ╭❤～代码如下：
import requests
import bs4
import re
import openpyxl
def open_url(url):
# 使用代理
# proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
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, proxies=proxies)
res = requests.get(url, headers=headers)
return res
def find_movies(res):
soup = bs4.BeautifulSoup(res.text, 'html.parser')
# 电影名
movies = []
targets = soup.find_all("div", class_="hd")
for each in targets:
movies.append(each.a.span.text)
# 评分
ranks = []
targets = soup.find_all("span", class_="rating_num")
for each in targets:
ranks.append(each.text)
# 资料
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(, ranks, messages])
return result
# 找出一共有多少个页面
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 excel(result):
wb = openpyxl.Workbook()
ws = wb.active
ws['A1'] = "电影名称"
ws['B1'] = "评分"
ws['C1'] = "资料"
for i in result:
ws.append(i)
ws.save("豆瓣top250")
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)'''
excel(result)
if __name__ == "__main__":
main()
ws.save("豆瓣top250") 应该改成 wb.save("豆瓣top250.xlsx")吧 请检查两处可能导致报错的地方：
确保已经安装了必要的库: requests、bs4 和 openpyxl。 安装方法：在命令行中执行以下命令进行安装：
pip install requests
pip install beautifulsoup4
pip install openpyxl
请检查代码中是否存在 "非打印ASCII字符"，如 "不间断空格" 等。 这些字符可能在我们看来看起来和空格无异，但却会导致解析器报错。要解决这个问题，可以手动删除所有的空格，并使用常规空格（即键盘上的空格）。
如果问题仍未解决，请提供具体的错误信息，以便更好地帮助您解决问题。 isdkz 发表于 2023-5-3 20:56
ws.save("豆瓣top250") 应该改成 wb.save("豆瓣top250.xlsx")吧
细节了 小甲鱼 发表于 2023-5-4 05:02
细节了
小甲鱼老师也还没睡？
页:
[1]