spider/EasySpider
1
0
Fork 0
mirror of https://github.com/NaiboWang/EasySpider.git synced 2025-04-20 10:05:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Bug fix for ...

Browse Source
This commit is contained in:
naibo 2024-07-12 20:24:05 +08:00
parent bf320abf1a
commit 072b6ad21e
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ExecuteStage/.vscode/launch.json vendored
View File

@ -12,7 +12,7 @@
"justMyCode": false, "justMyCode": false,
// "args": ["--ids", "[7]", "--read_type", "remote", "--headless", "0"] // "args": ["--ids", "[7]", "--read_type", "remote", "--headless", "0"]
// "args": ["--ids", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"] // "args": ["--ids", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"]
"args": ["--ids", "[0]", "--headless", "0", "--user_data", "0", "--keyboard", "0", "args": ["--ids", "[3]", "--headless", "0", "--user_data", "0", "--keyboard", "0",
"--read_type", "remote"] "--read_type", "remote"]
// "args": "--ids '[97]' --user_data 1 --server_address http://localhost:8074 --config_folder '/Users/naibo/Documents/EasySpider/ElectronJS/' --headless 0 --read_type remote --config_file_name config.json --saved_file_name" // "args": "--ids '[97]' --user_data 1 --server_address http://localhost:8074 --config_folder '/Users/naibo/Documents/EasySpider/ElectronJS/' --headless 0 --read_type remote --config_file_name config.json --saved_file_name"
} }

6
ExecuteStage/easyspider_executestage.py
View File

@ -239,7 +239,7 @@ class BrowserThread(Thread):
iframe = parameters.get('iframe') iframe = parameters.get('iframe')
option = node["option"] option = node["option"]
parameters["iframe"] = False if not iframe else ... parameters["iframe"] = False if not iframe else parameters.get('iframe', False)
if parameters.get("xpath"): if parameters.get("xpath"):
parameters["xpath"] = lowercase_tags_in_xpath(parameters["xpath"]) parameters["xpath"] = lowercase_tags_in_xpath(parameters["xpath"])
@ -274,7 +274,7 @@ class BrowserThread(Thread):
parameters["recordASField"] = param.get("recordASField", 1) parameters["recordASField"] = param.get("recordASField", 1)
param["splitLine"] = 0 if not param.get("splitLine") else ... param["splitLine"] = 0 if not param.get("splitLine") else param.get("splitLine")
if param.get("contentType") == 8: if param.get("contentType") == 8:
self.print_and_log("默认的ddddocr识别功能如果觉得不好用，可以自行修改源码get_content函数->contentType ==" self.print_and_log("默认的ddddocr识别功能如果觉得不好用，可以自行修改源码get_content函数->contentType =="
@ -301,7 +301,7 @@ class BrowserThread(Thread):
parameters["xpath"] = "" parameters["xpath"] = ""
self.print_and_log(f"您的任务版本号为{self.task_version}，循环点击不支持相对XPath写法，已自动切换为纯循环的XPath") self.print_and_log(f"您的任务版本号为{self.task_version}，循环点击不支持相对XPath写法，已自动切换为纯循环的XPath")
elif option == GraphOption.Loop.value: # 循环操作 elif option == GraphOption.Loop.value: # 循环操作
parameters['exitElement'] = "//body" if not parameters.get('exitElement') or parameters.get('exitElement') == "" else ... parameters['exitElement'] = "//body" if not parameters.get('exitElement') or parameters.get('exitElement') == "" else parameters.get('exitElement')
parameters["quickExtractable"] = False # 是否可以快速提取 parameters["quickExtractable"] = False # 是否可以快速提取
parameters['skipCount'] = parameters.get('skipCount', 0) parameters['skipCount'] = parameters.get('skipCount', 0)