gzh_spider_scrapy/gzh_spider/functions/get_video_url.py

import time
import json
import random
import requests
from selenium.webdriver import DesiredCapabilities
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium import webdriver


def find_video_url(article_url):
    # 打印请求配置
    ca = DesiredCapabilities.CHROME
    ca["goog:loggingPrefs"] = {"performance": "ALL"}

    # 不打开浏览器运行
    chrome_options = webdriver.ChromeOptions()
    chrome_options.add_argument("headless")
    chrome_options.add_argument(
        f"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36"
    )
    chrome_options.add_argument("--no-sandbox")

    driver = webdriver.Chrome(options=chrome_options)

    driver.implicitly_wait(random.randint(5, 10))

    driver.get(article_url)
    time.sleep(1)

    if (
            len(
                driver.find_elements(
                    By.XPATH, '//div[@class="js_video_poster video_poster"]/*[2]'
                )
            )
            != 0
    ):
        video_url = driver.find_element(
            By.XPATH, '//div[@class="js_video_poster video_poster"]/*[2]'
        ).get_attribute("src")
    elif (
            len(
                driver.find_elements(
                    By.XPATH, '//span[@class="js_tx_video_container"]/*[1]'
                )
            )
            != 0
    ):
        iframe = driver.find_element(
            By.XPATH, '//span[@class="js_tx_video_container"]/*[1]'
        ).get_attribute("src")
        video_id = iframe.split("vid=")[-1].split("&")[0]
        video_url = get_tencent_video_url(video_id)
    else:
        video_url = 0
    driver.quit()
    # print("successful find video url", video_url)
    return video_url


def get_tencent_video_url(video_id):
    url = (
            "https://vv.video.qq.com/getinfo?vids="
            + str(video_id)
            + "&platform=101001&charge=0&otype=json"
    )
    response = (
        requests.get(url=url).text.replace("QZOutputJson=", "").replace('"};', '"}')
    )
    response = json.loads(response)
    url = response["vl"]["vi"][0]["ul"]["ui"][0]["url"]
    fvkey = response["vl"]["vi"][0]["fvkey"]
    video_url = url + str(video_id) + ".mp4?vkey=" + fvkey
    return video_url