爬取快手视频

这里分享如何使用 nodejs 爬取快手用户发表的视频，仅供学习使用。

const { GraphQLClient, gql } = require("graphql-request");
//关键是 header 中要包含合格的 Cookie 值
async function app() {
  const url = "https://www.kuaishou.com/graphql";
  const client = new GraphQLClient(url);

  const query = gql`
    {
      visionProfilePhotoList(
        pcursor: ""
        userId: "3x4yuv5jbnnvyss"
        page: "profile"
      ) {
        result
        llsid
        webPageArea
        feeds {
          type
          author {
            id
            name
            following
            headerUrl
            headerUrls {
              cdn
              url
              __typename
            }
            __typename
          }
          tags {
            type
            name
            __typename
          }
          photo {
            id
            duration
            caption
            likeCount
            realLikeCount
            coverUrl
            coverUrls {
              cdn
              url
              __typename
            }
            photoUrls {
              cdn
              url
              __typename
            }
            photoUrl
            liked
            timestamp
            expTag
            animatedCoverUrl
            stereoType
            videoRatio
            profileUserTopPhoto
            __typename
          }
          canAddComment
          currentPcursor
          llsid
          status
          __typename
        }
        hostName
        pcursor
        __typename
      }
    }
  `;

  const variables = {
    pcursor: "",
    userId: "3x4yuv5jbnnvyss",
    page: "profile",
  };

  //Cookie最重要，其他好像都不需要
  const requestHeaders = {
    Cookie:
      "clientid=3; did=web_233037eca7abf4c900e88b73742835ee; client_key=65890b29; kpf=PC_WEB; kpn=KUAISHOU_VISION",
    Referer: "https://www.kuaishou.com/profile/3x4yuv5jbnnvyss",
    Origin: "https://www.kuaishou.com",
    "User-Agent":
      "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36 Edg/97.0.1072.55",
  };

  const data = await client
    .request(query, variables, requestHeaders)
    .catch((err) => {
      console.log("出错：", err);
    });

  console.log(data);
}

app();