FengHL 发表于 2021-6-6 15:37:09

没有生成Excel文件

使用Python读写Excel文件（1）课程，按照视频把代码改了，没有生成Excel文件！


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 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))

def save_to_excel(result):
    wb = openpyxl.Workbook()
    ws = wb.active

    ws['A1'] = "电影名称"
    ws['B1'] = "评分"
    ws['C1'] = "资料"

    for each in result:
      ws.append(each)

    wb.save("豆瓣top250电影。xlsx")
   
if __name__ == "__main__":
    main()
   

Twilight6 发表于 2021-6-6 15:37:10

本帖最后由 Twilight6 于 2021-6-6 15:48 编辑



你的 main 函数忘记调用 save_to_excel(result) 了，在 main 的函数最后加上 save_to_excel(result)

你 wb.save("豆瓣top250电影。xlsx") 写成 中文的 句号了... 改成英文的

参考代码：

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 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))
    save_to_excel(result)


def save_to_excel(result):
    wb = openpyxl.Workbook()
    ws = wb.active

    ws['A1'] = "电影名称"
    ws['B1'] = "评分"
    ws['C1'] = "资料"

    for each in result:
      ws.append(each)

    wb.save("豆瓣top250电影.xlsx")


if __name__ == "__main__":
    main()



FengHL 发表于 2021-6-6 15:49:22

本帖最后由 FengHL 于 2021-6-6 15:50 编辑

Twilight6 发表于 2021-6-6 15:46
你的 main 函数忘记调用 save_to_excel(result) 了，在 main 的函数最后加上 save_to_excel(result)

...

Twilight6 发表于 2021-6-6 15:50:05

FengHL 发表于 2021-6-6 15:49
改了，好像还是不行



main 函数加了 save_to_excel(result) 了嘛？

FengHL 发表于 2021-6-6 15:53:13

Twilight6 发表于 2021-6-6 15:50
main 函数加了 save_to_excel(result) 了嘛？

可以了，万分感谢
页: [1]
查看完整版本: 没有生成Excel文件