day3 6月26日 python爬虫 学习笔记 一 爬虫原理 二 Requests请求库

import requests  # 导入requests请求库


# 往百度主页发送请求，获取响应对象
response = requests.get(url='https://www.baidu.com/')

# 设置字符编码为 utf-8
response.encoding = 'utf-8'

# 打印响应文本
print(response.text)

# 把响应文本写入本地
with open('baidu.html', 'w', encoding='utf-8') as f:
    f.write(response.text)

''''''
'''
视频选项:
    1.梨视频
'''
# import requests
#
# # 往视频源地址发送请求
# response = requests.get(
#     'https://video.pearvideo.com/mp4/adshort/20190625/cont-1570302-14057031_adpkg-ad_hd.mp4')
#
# # 打印二进制流，比如图片、视频等数据
# print(response.content)
#
# # 保存视频到本地
# with open('视频.mp4', 'wb') as f:
#     f.write(response.content)

'''
1、先往梨视频主页发送请求
    https://www.pearvideo.com/
    
    解析获取所有视频的id:
        video_1570302
        
        re.findall()
        

2、获取视频详情页url:
    惊险!男子抢上地铁滑倒,就脚进去了
    https://www.pearvideo.com/video_1570302
    揭秘坎儿井
    https://www.pearvideo.com/video_1570107
'''
import requests
import re  # 正则，用于解析文本数据
# 1、先往梨视频主页发送请求
response = requests.get('https://www.pearvideo.com/')
# print(response.text)

# re正则匹配获取所有视频id
# 参数1: 正则匹配规则
# 参数2: 解析文本
# 参数3: 匹配模式
res_list = re.findall('<a href="video_(.*?)"', response.text, re.S)
# print(res_list)

# 拼接每一个视频详情页url
for v_id in res_list:
    detail_url = 'https://www.pearvideo.com/video_' + v_id
    # print(detail_url)

    # 对每一个视频详情页发送请求获取视 频源url
    response = requests.get(url=detail_url)
    # print(response.text)

    # 解析并提取详情页视频url
    # 视频url
    video_url = re.findall('srcUrl="(.*?)"', response.text, re.S)[0]
    print(video_url)

    # 视频名称
    video_name = re.findall(
        '<h1 class="video-tt">(.*?)</h1>', response.text, re.S)[0]

    print(video_name)

    # 往视频url发送请求获取视频二进制流
    v_response = requests.get(video_url)

    with open('%s.mp4' % video_name, 'wb') as f:
        f.write(v_response.content)
        print(video_name, '视频爬取完成')

''''''
'''
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)