Python爬取豆瓣电影+数据可视化，爬虫教程！

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&