Python爬虫下载西瓜视频

1、简介

由于西瓜视频免费，全站视频都可以下载，需要指定详情的视频链接，默认720P，电影内存1G多

2、Python

清单文件

requests==2.21.0

lxml==4.3.0

3、代码

from base64 import b64decode

from lxml import etree

import requests

import json

import re

import os

class XiGuaSpider:

def __init__(self):

self.headers = {

'Referer': 'https://www.ixigua.com',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',

'cookie': 'wafid=5b014d14-4285-413a-9dac-80e467ad5b4e; wafid.sig=Coe4SV6gStmKvfg897vmEd6h4_k; ttwid=6827754753289045508; ttwid.sig=hZChEHZDh7I1GdyST_waUAu31MA; xiguavideopcwebid=6827754753289045508; xiguavideopcwebid.sig=PPinOOHLyRkB7vLZeARYw7faelQ; SLARDAR_WEB_ID=91892236-9025-4d06-9d8e-1ec85233c784; _ga=GA1.2.15757958.1589710551; ixigua-a-s=1; _gid=GA1.2.1010024108.1589876453; s_v_web_id=kadne2g1_M7vfty8L_ecKr_47jB_8GWc_ctMlrqAXOgQy; _gat_gtag_UA_138710293_1=1',

}

self.video_dirs = './video'

def download_file(self, file_path, download_url):

print('*' * 100)

print(f"保存路径：{file_path}")

print(f'下载URL：{download_url}')

response = requests.get(url=download_url, headers=self.headers, stream=True)

content_size = int(response.headers["content-length"]) # 视频内容的总大小

size = 0

with open(file_path, "wb") as file: # 非纯文本都以字节的方式写入

for data in response.iter_content(chunk_size=1024): # 循环写入

file.write(data) # 写入视频文件

file.flush() # 刷新缓存

size += len(data) # 叠加每次写入的大小

# 打印下载进度

print("\r文件下载进度:%d%%(%0.2fMB/%0.2fMB)" % (

float(size / content_size * 100), (size / 1024 / 1024),

(content_size / 1024 / 1024)),

end=" ")

print()

def get_response(self, url):

response = None

try:

response = requests.get(url, headers=self.headers)

except Exception as e:

print(e)

return response

def parse_detail(self, url):

response = self.get_response(url)

if not response:

return

html = response.text

document = etree.HTML(html)

title = ''.join(document.xpath('//*[@class="hasSource"]/text()'))

if not title:

title = ''.join(document.xpath('//*[@class="teleplayPage__Description__header"]/h1/text()'))

title = re.sub(u"([^\u4e00-\u9fa5\u0030-\u0039\u0041-\u005a\u0061-\u007a])", "-", title)

pattern = r'\