Python爬取豆瓣电影Top250 + 数据可视化

我的这篇博客的一些代码解释python大作业电影演员数据分析

1. 爬取数据

1.1 导入以下模块

import os
import re
import time
import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
from openpyxl import Workbook, load_workbook

1.2 获取每页电影链接

def getonepagelist(url,headers):
    try:
        r = requests.get(url, headers=headers, timeout=10)
        r.raise_for_status()
        r.encoding = 'utf-8'
        soup = BeautifulSoup(r.text, 'html.parser')
        lsts = soup.find_all(attrs={'class': 'hd'})
        for lst in lsts:
            href = lst.a['href']
            time.sleep(0.5)
            getfilminfo(href, headers)
    except:
        print('getonepagelist error!')

1.3 获取每部电影具体信息

def getfilminfo(url,headers):
    filminfo = []
    r = requests.get(url, headers=headers, timeout=10)
    r.raise_for_status()
    r.encoding = 'utf-8'
    soup = BeautifulSoup(r.text, 'html.parser')

1.4 保存数据

def insert2excel(filepath,allinfo):
    try:
        if not os.path.exists(filepath):
            tableTitle = ['片名','上映年份','评分','评价人数','导演','编剧','主演','类型','国家/地区','语言','时长(分钟)']
            wb = Workbook()
            ws = wb.active
            ws.title = 'sheet1'
            ws.append(tableTitle)
            wb.save(filepath)
            time.sleep(3)
        wb = load_workbook(filepath)
        ws = wb.active
        ws.title = 'sheet1'
        ws.append(allinfo)
        wb.save(filepath)
        return True
    except:
        return False

2. 数据可视化

2.1 导入以下模块

import pandas as pd
from pyecharts import options as opts
from pyecharts.charts import Bar

2.2 用pandas模块读取数据

data = pd.read_excel('/home/mw/input/TOP2508837/TOP250.xlsx')
data.head(10)

2.3 各年份上映电影数量柱状图（纵向）

def getzoombar(data):
    year_counts = data['上映年份'].value_counts()
    year_counts.columns = ['上映年份', '数量']
    year_counts = year_counts.sort_index()
    c = (
        Bar()
        .add_xaxis(list(year_counts.index))
        .add_yaxis('上映数量', year_counts.values.tolist())
        .set_global_opts(
            title_opts=opts.TitleOpts(title='各年份上映电影数量'),
            yaxis_opts=opts.AxisOpts(name='上映数量'),
            xaxis_opts=opts.AxisOpts(name='上映年份'),
            datazoom_opts=[opts.DataZoomOpts(), opts.DataZoomOpts(type_='inside')],)
        )

2.4 各地区上映电影数量前十柱状图（横向）

def getcountrybar(data):
    country_counts = data['国家/地区'].value_counts()
    country_counts.columns = ['国家/地区', '数量']
    country_counts = country_counts.sort_values(ascending=True)
    c = (
        Bar()
        .add_xaxis(list(country_counts.index)[-10:])
        .add_yaxis('地区上映数量', country_counts.values.tolist()[-10:])
        .reversal_axis()
        .set_global_opts(
        title_opts=opts.TitleOpts(title='地区上映电影数量'),
        yaxis_opts=opts.AxisOpts(name='国家/地区'),
        xaxis_opts=opts.AxisOpts(name='上映数量'),
        )
        .set_series_opts(label_opts=opts.LabelOpts(position="right"))
        )

2.5 电影评价人数前二十柱状图（横向）

def getscorebar(data):
    df = data.sort_values(by='评价人数', ascending=True)
    c = (
        Bar()
        .add_xaxis(df['片名'].values.tolist()[-20:])
        .add_yaxis('评价人数', df['评价人数'].values.tolist()[-20:])
        .reversal_axis()
        .set_global_opts(
            title_opts=opts.TitleOpts(title='电影评价人数'),
            yaxis_opts=opts.AxisOpts(name='片名'),
            xaxis_opts=opts.AxisOpts(name='人数'),
            datazoom_opts=opts.DataZoomOpts(type_='inside'),
            )
        .set_series_opts(label_opts=opts.LabelOpts(position="right"))
        )

本文摘至“当打之年”