#pythonrun environmentPython3.9
#目标:爬取梨视频上的视频数据下载到本地
#分析网站:
# 1,数据来源 if ?{动态数据,or 静态数据}? 通过谷歌浏览器的检查判断源代码
# 2,数据抓包分析
#视频排行榜页面列表https://www.pearvideo.com/popular_loading.jsp?reqType=1&categoryId=&start=40&sort=39&mrd=0.3765578053919627(瀑布流加载方式翻页)通过检查network-XHR(popular_longing)
#结果为动态视频 https://www.pearvideo.com/video_1705502 目标视频播放网址
#视频链接存放:https://www.pearvideo.com/videoStatus.jsp?contId=1705502&mrd=0.6076594161036941 (通过network-XHR缓存地址)
#(假)视频播放地址https://video.pearvideo.com/mp4/adshort/20201105/1604657107043-15468144_adpkg-ad_hd.mp4(network-XHR-preview-videoinfo展开数据得到videourl)
#(真)视频播放地址:https://video.pearvideo.com/mp4/adshort/20201105/cont-1705502-15468144_adpkg-ad_hd.mp4(通过目标源代码Elements右键播放处选择检查源代码得到)
#流程:
# 1,url
# 2,发送请求,接受响应
# 3,解析网页
# 4,保存数据
import re
import requests
def get_url(video_id):
url = 'https://www.pearvideo.com/videoStatus.jsp?contId={}&mrd=0.6076594161036941'.format(video_id)
headers = {
#防盗链,确定来路
'Referer': 'https://www.pearvideo.com/video_{}'.format(video_id),
#用户代理 确定用户信息
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36',
}
response = requests.get(url,headers=headers)
# print(response.text)
html_data = response.json()
video_url = html_data['videoInfo']['videos']['srcUrl']
# print(video_url)
#正则表达式用于id 替换真url地址 cont- 构造真的链接地址
new_url = re.sub(r'\/\d{13}-',f'/cont-{video_id}-',video_url)
# print(new_url)
#存放视频地址
path = r'G:\video\\' + video_id + '.mp4' #很重要文件夹路径后面是两个\\ 不然后面出现’下面警告波浪线
resp = requests.get(new_url)
with open(path,mode='wb') as f:
f.write(resp.content) #.content用于保存二进制数据
for page in range(0,10,10):
url = 'https://www.pearvideo.com/popular_loading.jsp'
params = {
'reqType': '1',
'categoryId':'',
'start':'{}'.format(page),
'sort' : '1',
'mrd' :'0.3765578053919627',
}
response = requests.get(url,params=params)
# print(response.text)
titles = re.findall('<h2 class="popularem-title">(.*?)</h2>',response.text)
# print(titles)
num_id = re.findall('<a href="video_(\d+)" class="popularembd actplay">',response.text)
# print(num_id)
# 这里代表第几(0)个视频数(留空则默认上面1-10的视频)
get_url(num_id[0])
未经允许不得转载:萌萌Apprentissage » Python example, breaking the back-up, climbing and downloading the pear video
Python batches to extract mainstream search engine pictures
Python's word crawling across 100 degrees.
PythonTaiichi Taipei Artificial Intelligence Tensoflow Graphic Processing
Selenium with Tor Browser using Python
I'm gonna get you a new one, shell.cloud.google on the line.
run crontab with python selenium tor browser display in linux
Lineux Environment Use python to call the ter browser random browser web page