jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-04-21 11:17:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #764 from yangtao210/main

Browse Source 
新增存储到mongoDB
This commit is contained in:
程序员阿江-Relakkes
2025-11-06 06:10:49 -05:00
committed by GitHub
parent 45ec4b433a ef6948b305
commit 05a1782746
25 changed files with 1367 additions and 665 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
media_platform/bilibili/core.py
View File

@@ -497,11 +497,12 @@ class BilibiliCrawler(AbstractCrawler):
"height": 1080
},
user_agent=user_agent,
channel="chrome", # 使用系统的Chrome稳定版
)
return browser_context
else:
# type: ignore
browser = await chromium.launch(headless=headless, proxy=playwright_proxy)
browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel="chrome")
browser_context = await browser.new_context(viewport={"width": 1920, "height": 1080}, user_agent=user_agent)
return browser_context

3
media_platform/kuaishou/core.py
View File

@@ -333,10 +333,11 @@ class KuaishouCrawler(AbstractCrawler):
proxy=playwright_proxy, # type: ignore
viewport={"width": 1920, "height": 1080},
user_agent=user_agent,
channel="chrome", # 使用系统的Chrome稳定版
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel="chrome") # type: ignore
browser_context = await browser.new_context(
viewport={"width": 1920, "height": 1080}, user_agent=user_agent
)

3
media_platform/tieba/core.py
View File

@@ -614,10 +614,11 @@ class TieBaCrawler(AbstractCrawler):
proxy=playwright_proxy, # type: ignore
viewport={"width": 1920, "height": 1080},
user_agent=user_agent,
channel="chrome", # 使用系统的Chrome稳定版
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel="chrome") # type: ignore
browser_context = await browser.new_context(
viewport={"width": 1920, "height": 1080}, user_agent=user_agent
)

3
media_platform/weibo/core.py
View File

@@ -343,10 +343,11 @@ class WeiboCrawler(AbstractCrawler):
"height": 1080
},
user_agent=user_agent,
channel="chrome", # 使用系统的Chrome稳定版
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel="chrome") # type: ignore
browser_context = await browser.new_context(viewport={"width": 1920, "height": 1080}, user_agent=user_agent)
return browser_context

3
media_platform/zhihu/core.py
View File

@@ -429,10 +429,11 @@ class ZhihuCrawler(AbstractCrawler):
proxy=playwright_proxy, # type: ignore
viewport={"width": 1920, "height": 1080},
user_agent=user_agent,
channel="chrome", # 使用系统的Chrome稳定版
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel="chrome") # type: ignore
browser_context = await browser.new_context(
viewport={"width": 1920, "height": 1080}, user_agent=user_agent
)