#爬取梨視頻數據
import requests
import re
from lxml import etree
from multiprocessing.dummy import Pool
import random

# 定義獲取視頻數據方法
def getVideoData(url): # url為列表中的視頻url
  return requests.get(url=url,headers=headers).content

# 定義存儲數據方法
def saveVideo(data):
  fileName = str(random.randint(0,5000))+'.mp4'
  with open(fileName,'wb') as fp:
    fp.write(data)

# 爬取數據
#實例化一個線程池對象，開啟5個線程池
pool = Pool(5)

url = 'https://www.pearvideo.com/category_1'
headers = {
  'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@id="listvideoList"]/ul/li')

video_url_list = [] # 存的是將要下載視頻的url
for li in li_list:
  detail_url = 'https://www.pearvideo.com/'+li.xpath('./div/a/@href')[0]
  detail_page = requests.get(url=detail_url,headers=headers).text
  #因為視頻連接不在標簽匯中，而是一個js語句，所以用正則匹配
  video_url = re.findall('srcUrl="(.*?)",vdoUrl',detail_page,re.S)[0]
  video_url_list.append(video_url)
  
# map函數的應用：參數1：回調函數，參數2：列表；
#將列表中的參數賦值給回調函數的形參，讓回調函數處理
video_data_list = pool.map(getVideoData,video_url_list)

pool.map(saveVideo,video_data_list)