mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-10-07 12:38:11 +08:00
i18n: translate all Chinese comments, docstrings, and logger messages to English
Comprehensive translation of Chinese text to English across the entire codebase: - api/: FastAPI server documentation and logger messages - cache/: Cache abstraction layer comments and docstrings - database/: Database models and MongoDB store documentation - media_platform/: All platform crawlers (Bilibili, Douyin, Kuaishou, Tieba, Weibo, Xiaohongshu, Zhihu) - model/: Data model documentation - proxy/: Proxy pool and provider documentation - store/: Data storage layer comments - tools/: Utility functions and browser automation - test/: Test file documentation Preserved: Chinese disclaimer header (lines 10-18) for legal compliance 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
程序员阿江(Relakkes)
co-authored by
Claude Opus 4.5
Claude Opus 4.5
parent
1544d13dd5
commit
157ddfb21b
@@ -53,7 +53,7 @@ class DouYinLogin(AbstractLogin):
|
||||
async def begin(self):
|
||||
"""
|
||||
Start login douyin website
|
||||
滑块中间页面的验证准确率不太OK... 如果没有特俗要求，建议不开抖音登录，或者使用cookies登录
|
||||
The verification accuracy of the slider verification is not very good... If there are no special requirements, it is recommended not to use Douyin login, or use cookie login
|
||||
"""
|
||||
|
||||
# popup login dialog
|
||||
@@ -69,7 +69,7 @@ class DouYinLogin(AbstractLogin):
|
||||
else:
|
||||
raise ValueError("[DouYinLogin.begin] Invalid Login Type Currently only supported qrcode or phone or cookie ...")
|
||||
|
||||
# 如果页面重定向到滑动验证码页面，需要再次滑动滑块
|
||||
# If the page redirects to the slider verification page, need to slide again
|
||||
await asyncio.sleep(6)
|
||||
current_page_title = await self.context_page.title()
|
||||
if "验证码中间页" in current_page_title:
|
||||
@@ -147,10 +147,10 @@ class DouYinLogin(AbstractLogin):
|
||||
send_sms_code_btn = self.context_page.locator("xpath=//span[text() = '获取验证码']")
|
||||
await send_sms_code_btn.click()
|
||||
|
||||
# 检查是否有滑动验证码
|
||||
# Check if there is slider verification
|
||||
await self.check_page_display_slider(move_step=10, slider_level="easy")
|
||||
cache_client = CacheFactory.create_cache(config.CACHE_TYPE_MEMORY)
|
||||
max_get_sms_code_time = 60 * 2 # 最长获取验证码的时间为2分钟
|
||||
max_get_sms_code_time = 60 * 2 # Maximum time to get verification code is 2 minutes
|
||||
while max_get_sms_code_time > 0:
|
||||
utils.logger.info(f"[DouYinLogin.login_by_mobile] get douyin sms code from redis remaining time {max_get_sms_code_time}s ...")
|
||||
await asyncio.sleep(1)
|
||||
@@ -164,20 +164,20 @@ class DouYinLogin(AbstractLogin):
|
||||
await sms_code_input_ele.fill(value=sms_code_value.decode())
|
||||
await asyncio.sleep(0.5)
|
||||
submit_btn_ele = self.context_page.locator("xpath=//button[@class='web-login-button']")
|
||||
await submit_btn_ele.click() # 点击登录
|
||||
# todo ... 应该还需要检查验证码的正确性有可能输入的验证码不正确
|
||||
await submit_btn_ele.click() # Click login
|
||||
# todo ... should also check the correctness of the verification code, it may be incorrect
|
||||
break
|
||||
|
||||
async def check_page_display_slider(self, move_step: int = 10, slider_level: str = "easy"):
|
||||
"""
|
||||
检查页面是否出现滑动验证码
|
||||
Check if slider verification appears on the page
|
||||
:return:
|
||||
"""
|
||||
# 等待滑动验证码的出现
|
||||
# Wait for slider verification to appear
|
||||
back_selector = "#captcha-verify-image"
|
||||
try:
|
||||
await self.context_page.wait_for_selector(selector=back_selector, state="visible", timeout=30 * 1000)
|
||||
except PlaywrightTimeoutError: # 没有滑动验证码，直接返回
|
||||
except PlaywrightTimeoutError: # No slider verification, return directly
|
||||
return
|
||||
|
||||
gap_selector = 'xpath=//*[@id="captcha_container"]/div/div[2]/img[2]'
|
||||
@@ -191,16 +191,16 @@ class DouYinLogin(AbstractLogin):
|
||||
await self.move_slider(back_selector, gap_selector, move_step, slider_level)
|
||||
await asyncio.sleep(1)
|
||||
|
||||
# 如果滑块滑动慢了，或者验证失败了，会提示操作过慢，这里点一下刷新按钮
|
||||
# If the slider is too slow or verification failed, it will prompt "操作过慢", click the refresh button here
|
||||
page_content = await self.context_page.content()
|
||||
if "操作过慢" in page_content or "提示重新操作" in page_content:
|
||||
utils.logger.info("[DouYinLogin.check_page_display_slider] slider verify failed, retry ...")
|
||||
await self.context_page.click(selector="//a[contains(@class, 'secsdk_captcha_refresh')]")
|
||||
continue
|
||||
|
||||
# 滑动成功后，等待滑块消失
|
||||
# After successful sliding, wait for the slider to disappear
|
||||
await self.context_page.wait_for_selector(selector=back_selector, state="hidden", timeout=1000)
|
||||
# 如果滑块消失了，说明验证成功了，跳出循环，如果没有消失，说明验证失败了，上面这一行代码会抛出异常被捕获后继续循环滑动验证码
|
||||
# If the slider disappears, it means the verification is successful, break the loop. If not, it means the verification failed, the above line will throw an exception and be caught to continue the loop
|
||||
utils.logger.info("[DouYinLogin.check_page_display_slider] slider verify success ...")
|
||||
slider_verify_success = True
|
||||
except Exception as e:
|
||||
@@ -213,10 +213,10 @@ class DouYinLogin(AbstractLogin):
|
||||
async def move_slider(self, back_selector: str, gap_selector: str, move_step: int = 10, slider_level="easy"):
|
||||
"""
|
||||
Move the slider to the right to complete the verification
|
||||
:param back_selector: 滑动验证码背景图片的选择器
|
||||
:param gap_selector: 滑动验证码的滑块选择器
|
||||
:param move_step: 是控制单次移动速度的比例是1/10 默认是1 相当于 传入的这个距离不管多远0.1秒钟移动完 越大越慢
|
||||
:param slider_level: 滑块难度 easy hard,分别对应手机验证码的滑块和验证码中间的滑块
|
||||
:param back_selector: Selector for the slider verification background image
|
||||
:param gap_selector: Selector for the slider verification slider
|
||||
:param move_step: Controls the ratio of single movement speed, default is 1, meaning the distance moves in 0.1 seconds no matter how far, larger value means slower
|
||||
:param slider_level: Slider difficulty easy hard, corresponding to the slider for mobile verification code and the slider in the middle of verification code
|
||||
:return:
|
||||
"""
|
||||
|
||||
@@ -234,31 +234,31 @@ class DouYinLogin(AbstractLogin):
|
||||
)
|
||||
gap_src = str(await gap_elements.get_property("src")) # type: ignore
|
||||
|
||||
# 识别滑块位置
|
||||
# Identify slider position
|
||||
slide_app = utils.Slide(gap=gap_src, bg=slide_back)
|
||||
distance = slide_app.discern()
|
||||
|
||||
# 获取移动轨迹
|
||||
# Get movement trajectory
|
||||
tracks = utils.get_tracks(distance, slider_level)
|
||||
new_1 = tracks[-1] - (sum(tracks) - distance)
|
||||
tracks.pop()
|
||||
tracks.append(new_1)
|
||||
|
||||
# 根据轨迹拖拽滑块到指定位置
|
||||
# Drag slider to specified position according to trajectory
|
||||
element = await self.context_page.query_selector(gap_selector)
|
||||
bounding_box = await element.bounding_box() # type: ignore
|
||||
|
||||
await self.context_page.mouse.move(bounding_box["x"] + bounding_box["width"] / 2, # type: ignore
|
||||
bounding_box["y"] + bounding_box["height"] / 2) # type: ignore
|
||||
# 这里获取到x坐标中心点位置
|
||||
# Get x coordinate center position
|
||||
x = bounding_box["x"] + bounding_box["width"] / 2 # type: ignore
|
||||
# 模拟滑动操作
|
||||
# Simulate sliding operation
|
||||
await element.hover() # type: ignore
|
||||
await self.context_page.mouse.down()
|
||||
|
||||
for track in tracks:
|
||||
# 循环鼠标按照轨迹移动
|
||||
# steps 是控制单次移动速度的比例是1/10 默认是1 相当于 传入的这个距离不管多远0.1秒钟移动完 越大越慢
|
||||
# Loop mouse movement according to trajectory
|
||||
# steps controls the ratio of single movement speed, default is 1, meaning the distance moves in 0.1 seconds no matter how far, larger value means slower
|
||||
await self.context_page.mouse.move(x + track, 0, steps=move_step)
|
||||
x += track
|
||||
await self.context_page.mouse.up()
|
||||
|
||||
Reference in New Issue
Block a user