import requests
page = 1
keyword = 'xxxxx' # xxxxx為搜索的關(guān)鍵字
url = 'https://haokan.baidu.com/videoui/page/search?pn=%drn=10_format=jsontab=videoquery=%s'%(page,keyword)
res = requests.get(url)
data = res.json()

p = 'video class="video" src=(.*?)>'

def get_videoUrl(vid):
 '''
 提取視頻信息中的視頻源地址
 '''
 res = requests.get('https://haokan.baidu.com/v?vid=%s'%vid)
 html = res.text
 videoUrl = re.findall('video class="video" src=(.*?)>',html)[0]
 return videoUrl

def download_video(vid):
 '''
 下載視頻文件
 '''
 savePath = 'xxxxx.mp4' # 定義存儲(chǔ)的文件名
 videoUrl = get_videoUrl(vid) # 獲取視頻下載地址 
 res = requests.get(videoUrl)
 with open(savePath,'wb') as f:
 f.write(res.content)

# =============================================================================
# 好看視頻_v0.1
# =============================================================================
import re
import os
import time
import queue
import requests
import threading
import pandas as pd

class Haokan:
 def __init__(self):
 self.url = 'https://haokan.baidu.com/videoui/page/search?pn=%drn=20_format=jsontab=videoquery=%s'
 self.headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:80.0) Gecko/20100101 Firefox/80.0',
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
  'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
  'Connection': 'keep-alive',
  'Upgrade-Insecure-Requests': '1',
  'TE': 'Trailers',
 }
 self.savaPath = './videos' # 視頻存儲(chǔ)路徑
 
 def get_info(self,keywords,page):
 '''
 搜索關(guān)鍵字，獲取相關(guān)視頻信息
 '''
 self.result = [] # 相關(guān)視頻信息
 for p in range(1,page+1):
  res = requests.get(self.url%(p,keywords),headers=self.headers)
  data = res.json()['data']['response']
  videos = data['list']
  self.result.extend(videos)
  print('"第%d頁(yè)"爬取完成!'%(p+1))
 self.result = pd.DataFrame(self.result)
 self.result.to_excel('%s.xlsx'%keywords,index=False)
 # 定義隊(duì)列，用于多線程下載視頻
 self.url_queue = queue.Queue() 
 for vid,url in zip(self.result['vid'],self.result['url']):
  self.url_queue.put((vid,url))
 
 def get_videoUrl(self,url):
 '''
 提取視頻信息中的視頻源地址
 '''
 res = requests.get(url,headers=self.headers)
 html = res.text
 videoUrl = re.findall('video class="video" src=(.*?)>',html)[0]
 return videoUrl
 
 def download_video(self,videoId,videoUrl):
 '''
 下載視頻文件
 '''
 # 如果視頻存儲(chǔ)目錄不存在則創(chuàng)建
 if not os.path.exists(self.savaPath):
  os.mkdir(self.savaPath)
 res = requests.get(videoUrl,headers=self.headers)
 with open('%s/%s.mp4'%(self.savaPath,videoId),'wb') as f:
  f.write(res.content)
  
 def run(self):
 while not self.url_queue.empty():
  t_s = time.time()
  vid,url = self.url_queue.get()
  try:
  video_url = self.get_videoUrl(url)
  self.download_video(vid,video_url)
  except:
  print('"%s.mp4"下載失敗!'%vid)
  continue
  t_e = time.time()
  print('"%s.mp4"下載完成!(用時(shí)%.2fs)'%(vid,t_e-t_s))
  
if __name__ == "__main__":
 keywords = '多啦A夢(mèng)'
 page = 1 # 爬取頁(yè)數(shù)，每頁(yè)20條信息
 t_s = time.time()
 haokan = Haokan()
 haokan.get_info(keywords,page)
 N_thread = 3 # 線程數(shù)
 thread_list = []
 for i in range(N_thread):
 thread_list.append(threading.Thread(target=haokan.run))
 for t in thread_list:
 t.start()
 for t in thread_list:
 t.join()
 t_e = time.time()
 print('任務(wù)完成!(用時(shí)%.2fs)'%(t_e-t_s))