Python自动化我选DrissionPage，弃用Selenium

news2024/9/24 14:29:58

DrissionPage 是一个基于 python 的网页自动化工具。

它既能控制浏览器，也能收发数据包，还能把两者合而为一。

可兼顾浏览器自动化的便利性和 requests 的高效率。

它功能强大，内置无数人性化设计和便捷功能。

它的语法简洁而优雅，代码量少，对新手友好。

以下是我使用DrissionPage做的抖音无水印视频提取代码：

douyin.py:

# ---encoding:utf-8---
# @Time    : 2024/1/13 16:43
# @Author  : stzz Wang
# @Email   ：1050100468@qq.com
# @Site    : 
# @File    : douyin.py
# @Project : douyi_analysis
# @Software: PyCharm
import os
import sys

BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
sys.path.append(BASE_DIR)

from DrissionPage import ChromiumOptions, SessionOptions, WebPage
from CODES.config.CONFIG import *


class DouYin:
    def __init__(self):
        co = ChromiumOptions(ini_path=Config.drission_page_init_file_path)
        so = SessionOptions(ini_path=Config.drission_page_init_file_path)

        self.page = WebPage(chromium_options=co, session_or_options=so)


    def start_listen(self):
        self.page.listen.start()

    def end_listen(self):
        self.page.listen.pause(True)
        self.page.listen.stop()

    def load_page(self, url):
        self.page.get(url)

douyin_without_watermarker_analysis.py:

# ---encoding:utf-8---
# @Time    : 2024/1/13 16:53
# @Author  : stzz Wang
# @Email   ：1050100468@qq.com
# @Site    : 
# @File    : douyin_without_watermarker_analysis.py
# @Project : douyi_analysis
# @Software: PyCharm
import os
import sys
import time

BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
sys.path.append(BASE_DIR)

from fastapi import APIRouter
from CODES.controllers.model.douyin import *
from CODES.config.CONFIG import *
import json
from pydantic import BaseModel

douyin_wwa = APIRouter()

douyin_instance = DouYin()


class DouYinWithoutWatermarker(BaseModel):
    url: str


@douyin_wwa.post("/douyin_without_watermarker_analysis")
async def douyin_without_watermarker_analysis(accept: DouYinWithoutWatermarker):
    douyin_instance.load_page(accept.url)
    douyin_instance.start_listen()
    page = douyin_instance.page
    start_time = time.time()
    try:
        while True:
            res = page.listen.wait()  # 等待并获取一个数据包
            if "https://www.douyin.com/aweme/v1/web/aweme/post/" in res.url:
                data = json.loads(res._raw_body)
                data_list = data["aweme_list"]
                data = []
                for item in data_list:
                    d = {
                        "title" : item["desc"],
                        "urls" : item["video"]["play_addr"]["url_list"]
                    }
                    data.append(d)
                break

        use_time = time.time() - start_time
        data = {
            "data": data,
            "use_time": use_time
        }
    except Exception as e:
        data = {
            "data": e,
            "error_code": 500
        }
    finally:
        douyin_instance.end_listen()
    return data

完整代码在github上：

GitHub - STZZ-1992/douyin_analysis: 抖音短视频无水印的解析服务抖音短视频无水印的解析服务. Contribute to STZZ-1992/douyin_analysis development by creating an account on GitHub.https://github.com/STZZ-1992/douyin_analysis