python 豆瓣电影top250_[python爬虫]豆瓣电影Top250简单数据分析绘图

一：简介

通过抓取豆瓣电影Top250的数据，分别进行了三个数据统计，分别是：上榜的电影上映的年份，该年份总共上榜的电影数量，数量为0的就没有统计了；各个国家地区出品的电影数量；250部电影的各个类型标签的数量。

二：源代码

#coding=utf-8

import requests

from bs4 import BeautifulSoup

import os, socket, re

import matplotlib as mpl

import matplotlib.pyplot as plt

import numpy as np

class Spider:

def __init__(self, url='https://movie.douban.com/top250'):

self.url = url

self.header = {

"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"

}

def mkdir(self, path):

path = path.strip()

isExists = os.path.exists(os.path.join("D:\mdouban", path))

if not isExists:

os.makedirs(os.path.join("D:\mdouban", path))

os.chdir(os.path.join("D:\mdouban", path))

else:

os.chdir(os.path.join("D:\mdouban", path))

return os.path.abspath('.')

#获取BeautifulSoup

def get_soup(self, link):

html = requests.get(link, headers=self.header)

html.encoding = html.apparent_encoding

soup = BeautifulSoup(html.text, 'lxml')

return soup

if __name__ == '__main__':

socket.setdefaulttimeout(20)

spider = Spider()

path = spider.mkdir('top250')

print('starting get data from douban...')

def autolabel(rects, ax, xpos='center'): #设置显示每一个条形图的值

"""

Attach a text label above each bar in *rects*, displaying its height.