python爬虫实践——爬取“梨视频”

1 # 爬取梨视频
2 import requests
3 url=‘https://video.pearvideo.com/mp4/adshort/20190613/cont-1565846-14013215_adpkg-ad_hd.mp4‘
4 res = requests.get(url)
5 #将爬取的视频写入文件
6 with open(‘梨视频.mp4‘, ‘wb‘) as f:
7     f.write(res.content)

 1 import requests
 2 import re
 3 import uuid
 4 
 5 #1、发送请求
 6 def get_page(url):
 7     response=requests.get(url)
 8     return response
 9 
10 #2、解析数据
11 def parse_index(text):
12     res=re.findall(‘<a href="video_(.*?)"‘,text,re.S)
13 
14     detail_url_list=[]
15     for m_id in res:
16         detail_url=‘https://www.pearvideo.com/video_‘+m_id
17         detail_url_list.append(detail_url)
18 
19     return detail_url_list
20 
21 #解析详情页获取视频url
22 def parse_detail(text):
23     movie_url=re.findall(‘srcUrl="(.*?)"‘,text,re.S)[0]
24     return movie_url
25 
26 #3、保存数据
27 def save_movie(movie_url):
28     response=requests.get(movie_url)
29     with open(f‘{uuid.uuid4()}.mp4‘,‘wb‘)as f:
30         f.write(response.content)
31         f.flush()
32 
33 
34 #主函数:(输入‘main‘,然后按”回车“)
35 if __name__ == ‘__main__‘:
36     #1、对主页发送请求
37     index_res=get_page(url=‘https://www.pearvideo.com/‘)
38     #2、对主页进行解析、获取详情页id
39     detail_url_list=parse_index(index_res.text)
40 
41     #3、对每个详情页url发送请求
42     for detail_url in detail_url_list:
43         detail_res=get_page(url=detail_url)
44 
45         #4、解析详情页获取视频url
46         movie_url=parse_detail(detail_res.text)
47         print(movie_url)
48 
49         #5、保存视频
50         save_movie(movie_url)

 1 import requests
 2 import re  # 正则模块
 3 # uuid.uuid4()  可以根据时间戳生成一段世界上唯一的随机字符串
 4 import uuid
 5 # 导入线程池模块
 6 from concurrent.futures import ThreadPoolExecutor
 7 # 线程池限制50个线程
 8 pool = ThreadPoolExecutor(50)
 9 
10 # 爬虫三部曲
11 
12 # 1、发送请求
13 def get_page(url):
14     print(f‘开始异步任务: {url}‘)
15     response = requests.get(url)
16     return response
17 
18 
19 # 2、解析数据
20 # 解析主页获取视频详情页ID
21 def parse_index(res):
22 
23     response = res.result()
24     # 提取出主页所有ID
25     id_list = re.findall(‘<a href="video_(.*?)"‘, response.text, re.S)
26     # print(res)
27 
28     # 循环id列表
29     for m_id in id_list:
30         # 拼接详情页url
31         detail_url = ‘https://www.pearvideo.com/video_‘ + m_id
32         # print(detail_url)
33         # 把详情页url提交给get_page函数
34         pool.submit(get_page, detail_url).add_done_callback(parse_detail)
35 
36 
37 # 解析详情页获取视频url
38 def parse_detail(res):
39     response = res.result()
40     movie_url = re.findall(‘srcUrl="(.*?)"‘, response.text, re.S)[0]
41     # 异步提交把视频url传给get_page函数,把返回的结果传给save_movie
42     pool.submit(get_page, movie_url).add_done_callback(save_movie)
43 
44 
45 # 3、保存数据
46 def save_movie(res):
47 
48     movie_res = res.result()
49 
50     # 把视频写到本地
51     with open(f‘{uuid.uuid4()}.mp4‘, ‘wb‘) as f:
52         f.write(movie_res.content)
53         print(f‘视频下载结束: {movie_res.url}‘)
54         f.flush()
55 
56 
57 if __name__ == ‘__main__‘:  # main + 回车键
58 
59     # 一 往get_page发送异步请求，把结果交给parse_index函数
60     url = ‘https://www.pearvideo.com/‘
61     pool.submit(get_page, url).add_done_callback(parse_index)