Commit 73e25c43 authored by liyang's avatar liyang

fix:脚本执行异常未退出

parent 290453ef
...@@ -11,7 +11,7 @@ from datetime import datetime ...@@ -11,7 +11,7 @@ from datetime import datetime
from utils.download_image import download_image from utils.download_image import download_image
import os import os
from config.settings import get_base_file_url from config.settings import get_base_file_url
import sys
# 工具函数-下载图片 # 工具函数-下载图片
''' '''
打开指定网页,并使用 Selenium 模拟点击 "GDPR-accept" 按钮,然后循环点击 "search-show-more-button" 按钮来加载更多数据,直到按钮不再可点击为止。最后,获取完整的分页数据并关闭浏览器驱动。 打开指定网页,并使用 Selenium 模拟点击 "GDPR-accept" 按钮,然后循环点击 "search-show-more-button" 按钮来加载更多数据,直到按钮不再可点击为止。最后,获取完整的分页数据并关闭浏览器驱动。
...@@ -162,7 +162,14 @@ def reptile(browser=None, search_word=""): ...@@ -162,7 +162,14 @@ def reptile(browser=None, search_word=""):
else: else:
# 爬取数据为空 # 爬取数据为空
log.info("未爬取到数据") log.info("未爬取到数据")
browser.quit()
# 关闭浏览器驱动
try:
browser.close()
browser.quit()
sys.exit()
except:
log.debug("浏览器驱动关闭失败")
def main(): def main():
......
import io import io
import json import json
import re import re
import sys
import time import time
import loguru import loguru
# import pymysql.cursors # import pymysql.cursors
import requests import requests
...@@ -18,6 +18,7 @@ from utils.filse import save_json ...@@ -18,6 +18,7 @@ from utils.filse import save_json
import os import os
from config.settings import get_base_file_url from config.settings import get_base_file_url
from utils.download_image import download_image from utils.download_image import download_image
''' '''
爬取台湾PTT论坛的热门帖子,包括帖子的标题、内容【文本、图片、视频】 爬取台湾PTT论坛的热门帖子,包括帖子的标题、内容【文本、图片、视频】
...@@ -202,8 +203,12 @@ def reptile(browser=None, search_word=""): ...@@ -202,8 +203,12 @@ def reptile(browser=None, search_word=""):
log.info("未爬取到数据") log.info("未爬取到数据")
# 关闭浏览器驱动 # 关闭浏览器驱动
# time.sleep(3) try:
browser.quit() browser.close()
browser.quit()
sys.exit()
except:
log.debug("浏览器驱动关闭失败")
def main(): def main():
......
...@@ -8,6 +8,7 @@ from api.index import importJson, getReptileTask, importJsonPath ...@@ -8,6 +8,7 @@ from api.index import importJson, getReptileTask, importJsonPath
from utils.index import convert_to_traditional, yt_dlp_download, convert_string_to_time, parse_twitter_time_string from utils.index import convert_to_traditional, yt_dlp_download, convert_string_to_time, parse_twitter_time_string
# from pytube import YouTube # from pytube import YouTube
import os import os
import sys
from datetime import datetime from datetime import datetime
from utils.download_image import download_image from utils.download_image import download_image
from config.settings import get_base_file_url from config.settings import get_base_file_url
...@@ -163,8 +164,12 @@ def reptile(browser=None, search_word=""): ...@@ -163,8 +164,12 @@ def reptile(browser=None, search_word=""):
log.info("未爬取到数据") log.info("未爬取到数据")
# 关闭浏览器驱动 # 关闭浏览器驱动
# time.sleep(3) try:
browser.quit() browser.close()
browser.quit()
sys.exit()
except:
log.debug("浏览器驱动关闭失败")
def main(): def main():
......
...@@ -11,7 +11,7 @@ from datetime import datetime ...@@ -11,7 +11,7 @@ from datetime import datetime
import os import os
from config.settings import get_base_file_url from config.settings import get_base_file_url
from selenium.webdriver.common.action_chains import ActionChains from selenium.webdriver.common.action_chains import ActionChains
import sys
def reptile(browser=None, search_word=""): def reptile(browser=None, search_word=""):
""" """
...@@ -77,9 +77,14 @@ def reptile(browser=None, search_word=""): ...@@ -77,9 +77,14 @@ def reptile(browser=None, search_word=""):
else: else:
# 爬取数据为空 # 爬取数据为空
log.info("未爬取到数据") log.info("未爬取到数据")
browser.close()
# 关闭浏览器驱动 # 关闭浏览器驱动
browser.quit() try:
browser.close()
browser.quit()
sys.exit()
except:
log.debug("浏览器驱动关闭失败")
def main(): def main():
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment