爬虫 Day03

import requests

respones=requests.get(url='http://www.baidu.com')
respones.encoding='UTF-8'
print(respones.text)

with open ('badui.html','w',encoding='UTF-8')as f:
    f.write(respones.text)#爬baidu主页写成HTML

今日学习：

爬豆瓣

https://movie.douban.com/top250?start=0&filter=
https://movie.douban.com/top250?start=25&filter=
https://movie.douban.com/top250?start=50&filter=

1.发送请求
2.解析数据
3.保存数据
'''
import requests
import re

# 爬虫三部曲
# 1.发送请求
def get_page(base_url):
    response = requests.get(base_url)
    return response

# 2.解析文本
def parse_index(text):

    res = re.findall('<div class="item">.*?<em class="">(.*?)</em>.*?<a href="(.*?)">.*?<span class="title">(.*?)</span>.*?导演:(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价</span>.*?<span class="inq">(.*?)</span>', text, re.S)
    # print(res)
    return res

# 3.保存数据
def save_data(data):
    with open('douban.txt', 'a', encoding='utf-8') as f:
        f.write(data)

# main + 回车键
if __name__ == '__main__':
    # num = 10
    # base_url = 'https://movie.douban.com/top250?start={}&filter='.format(num)

    num = 0
    for line in range(10):
        base_url = f'https://movie.douban.com/top250?start={num}&filter='
        num += 25
        print(base_url)

        # 1.发送请求，调用函数
        response = get_page(base_url)

        # 2.解析文本
        movie_list = parse_index(response.text)

        # 3.保存数据
        # 数据的格式化
        for movie in movie_list:
            # print(movie)

            # 解压赋值
            # 电影排名、电影url、电影名称、导演 - 主演 - 类型、电影评分、评价人数、电影简介
            v_top, v_url, v_name, v_daoyan, v_point, v_num, v_desc = movie
            # v_top = movie[0]
            # v_url = movie[1]
            moive_content = f'''
            电影排名: {v_top}
            电影url: {v_url}
            电影名称: {v_name}
            导演主演: {v_daoyan}
            电影评分: {v_point}
            评价人数: {v_num}
            电影简介: {v_desc}
            \n
            '''

            print(moive_content)

            # 保存数据
            save_data(moive_content)