柚子快報激活碼778899分享：今天開始學(xué)爬蟲

http://yzkb.51969.com/

import requests

from bs4 import BeautifulSoup

import pandas as pd

base_url = "https://movie.douban.com/top250"

headers = {

"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"}

def fetch_page_data(url):

response = requests.get(url, headers=headers)

soup = BeautifulSoup(response.text, "html.parser")

movie_items = soup.find_all('div', class_='item')

data = []

for item in movie_items:

rank = item.find('em').text

title = item.find('span', class_='title').text

link = item.find('a')['href']

image = item.find('img')['src']

rating = item.find('span', class_='rating_num').text

num_reviews = item.find('div', class_='star').find_all('span')[-1].text[:-3]

summary = item.find('span', class_='inq').text if item.find('span', class_='inq') else ""

# 獲取導(dǎo)演信息

director = item.find('p').text.split('\n')[1].strip().split(' ')[1]

data.append({

'Rank': rank,

'Title': title,

'Link': link,

'Image': image,

'Rating': rating,

'Number of Reviews': num_reviews,

'Summary': summary,

'Director': director

})

return data

all_data = []

for i in range(0, 250, 25):

url = f"{base_url}?start={i}&filter="

all_data.extend(fetch_page_data(url))

df = pd.DataFrame(all_data)

df.to_excel("Douban_Top_250_Movies.xlsx", index=False)

print("Data has been saved to Douban_Top_250_Movies.xlsx")

import pandas as pd

import matplotlib.pyplot as plt

# 加載數(shù)據(jù)

df = pd.read_excel("Douban_Top_250_Movies.xlsx", engine='openpyxl')

plt.rcParams['font.sans-serif'] = ['SimHei']

plt.rcParams['axes.unicode_minus'] = False

# 查看數(shù)據(jù)規(guī)模及字段的數(shù)據(jù)類型

print("數(shù)據(jù)規(guī)模:", df.shape)

print("字段數(shù)據(jù)類型:\n", df.dtypes)

# 查看字段的統(tǒng)計信息

print("統(tǒng)計信息:\n", df.describe())

# 刪除缺失值記錄

clean_df = df.dropna()

print("處理后記錄數(shù):", clean_df.shape[0])

# 保存清洗后的數(shù)據(jù)

clean_df.to_excel("Douban_Top_250_Movies_Clean.xlsx", index=False)

# 可視化1: 任選10部電影名稱評分柱狀圖

plt.figure(figsize=(10, 5))

sample_movies = clean_df.sample(10)

plt.bar(sample_movies['Title'], sample_movies['Rating'], color='pink')

plt.xlabel('電影名稱')

plt.ylabel('評分')

plt.title('XX - 10部電影評分柱狀圖')

plt.xticks(rotation=45)

plt.tight_layout()

plt.savefig('Visualization_1.png')

plt.show()

# 可視化2: 任選4位導(dǎo)演上榜電影數(shù)量柱狀圖

directors = clean_df['Director'].value_counts().index[:4]

director_counts = clean_df['Director'].value_counts().values[:4]

plt.figure(figsize=(10, 5))

plt.bar(directors, director_counts, color='green')

plt.xlabel('導(dǎo)演')

plt.ylabel('上榜電影數(shù)量')

plt.title('從聰202209305 - 導(dǎo)演上榜電影數(shù)量柱狀圖')

plt.tight_layout()

plt.savefig('Visualization_2.png')

plt.show()

# 可視化3: 10部電影評論人數(shù)趨勢圖

sample_movies = clean_df.sample(10)

plt.figure(figsize=(10, 5))

plt.plot(sample_movies['Title'], sample_movies['Number of Reviews'], marker='o', linestyle='-', color='orange')

plt.xlabel('電影名稱')

plt.ylabel('評論人數(shù)')

plt.title('XX - 10部電影評論人數(shù)趨勢圖')

plt.xticks(rotation=45)

plt.tight_layout()

plt.savefig('Visualization_3.png')

plt.show()

柚子快報激活碼778899分享：今天開始學(xué)爬蟲

http://yzkb.51969.com/

相關(guān)文章