Python数据挖掘实战11:爬取豆瓣电影top250的电影数据

代码实例

# coding:utf8
# 1. 调用相关库
import requests, re
from bs4 import BeautifulSoup
from openpyxl import Workbook

# 2. 创建数据录入表格并添加表标题
wb = Workbook()
dest_filename = '豆瓣电影top250.xlsx'
ws1 = wb.active
ws1.title = "豆瓣电影top250"

# 3. 获取网页中的内容
douban_url = 'http://movie.douban.com/top250/'
def download_page(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'}
    data = requests.get(url, headers=headers).content
    return data

# 4. 电影数据信息分类、清洗
def get_li(doc):
    soup = BeautifulSoup(doc, 'html.parser')
    ol = soup.find('ol', class_='grid_view')
    name = []  # 名字
    star_con = []  # 评价人数
    score = []  # 评分
    info_list = []  # 短评

    for i in ol.find_all('li'):
        detail = i.find('div', attrs={'class': 'hd'})
        movie_name = detail.find('span', attrs={'class': 'title'}).get_text()  # 电影名字
        level_star = i.find('span', attrs={'class': 'rating_num'}).get_text()  # 评分
        star = i.find('div', attrs={'class': 'star'})
        star_num = star.find(text=re.compile('评价'))  # 评价
        info = i.find('span', attrs={'class': 'inq'})  # 短评
        if info:  # 判断是否有短评
            info_list.append(info.get_text())
        else:
            info_list.append('无')
        score.append(level_star)

        name.append(movie_name)
        star_con.append(star_num)
    page = soup.find('span', attrs={'class': 'next'}).find('a')  # 获取下一页
    if page:
        return name, star_con, score, info_list, douban_url + page['href']
    return name, star_con, score, info_list, None

# 5. 将电影数据录入表格
def main():
    url = douban_url
    name = []
    star_con = []
    score = []
    info = []
    while url:
        doc = download_page(url)
        movie, star, level_num, info_list, url = get_li(doc)
        name = name + movie
        star_con = star_con + star
        score = score + level_num
        info = info + info_list
    for (i, m, o, p) in zip(name, star_con, score, info):
        col_A = 'A%s' % (name.index(i) + 1)
        col_B = 'B%s' % (name.index(i) + 1)
        col_C = 'C%s' % (name.index(i) + 1)
        col_D = 'D%s' % (name.index(i) + 1)
        ws1[col_A] = i
        ws1[col_B] = m
        ws1[col_C] = o
        ws1[col_D] = p
    wb.save(filename=dest_filename)

# 6. 调用main()方法执行程序
if __name__ == '__main__':
    main()

运行结果

Python数据挖掘实战11:爬取豆瓣电影top250的电影数据

上一篇:Github


下一篇:保姆级教程,如何发现 GitHub 上的优质项目?