wangshaoqing/douyin-crawler-poc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: wangshaoqing:cb7f2c89f78d802dcf4e044a7ab6aafb22f24385
Branches Tags
wangshaoqing:main
..
compare: wangshaoqing:4c33f40289a4e2288f2fc92f7739c6c3ffe6fc6f
Branches Tags
wangshaoqing:main

No commits in common. "cb7f2c89f78d802dcf4e044a7ab6aafb22f24385" and "4c33f40289a4e2288f2fc92f7739c6c3ffe6fc6f" have entirely different histories.
cb7f2c89f7 ... 4c33f40289

1 changed files with 1 additions and 2 deletions
Show Stats Expand all files Collapse all files

3
Douyin.py
View File

@ -27,7 +27,6 @@ DEFAULT_USER_URL = (
) )
DEFAULT_BROWSER_PORT = 9223 DEFAULT_BROWSER_PORT = 9223
LISTEN_TARGET = "web/aweme/post/" LISTEN_TARGET = "web/aweme/post/"
RECOMMENDATION_LISTEN_TARGET = "aweme/v2/web/module/feed/"
SINGLE_VIDEO_LISTEN_TARGET = "web/aweme/detail/" SINGLE_VIDEO_LISTEN_TARGET = "web/aweme/detail/"
INVALID_FILENAME_CHARS = re.compile(r'[\\/:*?"<>|\r\n\t]') INVALID_FILENAME_CHARS = re.compile(r'[\\/:*?"<>|\r\n\t]')
RECOMMENDATION_URL_PATTERN = re.compile(r"^https?://www\.douyin\.com/?(?:\?.*)?$") RECOMMENDATION_URL_PATTERN = re.compile(r"^https?://www\.douyin\.com/?(?:\?.*)?$")
@ -399,7 +398,7 @@ def collect_recommendations(
if browser_port is not None: if browser_port is not None:
ensure_browser_debug_port_ready(browser_port) ensure_browser_debug_port_ready(browser_port)
page = create_page(chromium_page_cls, chromium_options_cls, browser_port) page = create_page(chromium_page_cls, chromium_options_cls, browser_port)
page.listen.start(RECOMMENDATION_LISTEN_TARGET) page.listen.start(LISTEN_TARGET)
print("[INFO] 正在打开抖音推荐流。若出现登录或验证码，请先在浏览器窗口里完成。") print("[INFO] 正在打开抖音推荐流。若出现登录或验证码，请先在浏览器窗口里完成。")
page.get("https://www.douyin.com/") page.get("https://www.douyin.com/")