imdb文本爬取及数据清理

imdb电影爬取代码

import requests
from bs4 import BeautifulSoup
import pandas as pd
import time
import numpy as np
import random

def bs_dealing(bs):
    movies_lst = []
    global page
    for movie in bs.findAll('div', {'class': 'lister-item-content'}):
        title = movie.find('a').string
        year = movie.find('span', {
            'class': 'lister-item-year text-muted unbold'
        }).string
        genres = movie.find('span', 'genre').string
        genres = genres.strip('\n').strip()
        # 控制网页返回的错误，runtime是否为空，以免数据无法正常写入
        if movie.find('span', 'runtime') is not None:
            runtime = movie.find('span', 'runtime').string
        else:
            runtime = 0
        rating = movie.find('div', {
            'class': "inline-block ratings-imdb-ra