spider/EasySpider
1
0
Fork 0
mirror of https://github.com/NaiboWang/EasySpider.git synced 2025-04-21 21:25:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Deal with data:

Browse Source
This commit is contained in:
naibo 2023-11-23 03:14:31 +08:00
parent 7edb1ec628
commit 1e5ecf8874
5 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/123.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/124.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/125.json Normal file
View File

File diff suppressed because one or more lines are too long

2
.temp_to_pub/EasySpider_windows_x64/tasks/209.json
View File

File diff suppressed because one or more lines are too long

6
ExecuteStage/easyspider_executestage.py
View File

@ -1032,6 +1032,9 @@ class BrowserThread(Thread):
self.browser.execute_script('window.stop()') self.browser.execute_script('window.stop()')
except: except:
pass pass
if self.browser.current_url.startswith("data:"):
self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
time.sleep(2)
if int(node["parameters"]["breakMode"]) > 0: # 如果设置了退出循环的脚本条件 if int(node["parameters"]["breakMode"]) > 0: # 如果设置了退出循环的脚本条件
output = self.execute_code(int( output = self.execute_code(int(
node["parameters"]["breakMode"]) - 1, node["parameters"]["breakCode"], node["parameters"]["breakCodeWaitTime"], iframe=node["parameters"]["iframe"]) node["parameters"]["breakMode"]) - 1, node["parameters"]["breakCode"], node["parameters"]["breakCodeWaitTime"], iframe=node["parameters"]["iframe"])
@ -1094,6 +1097,9 @@ class BrowserThread(Thread):
self.browser.execute_script('window.stop()') self.browser.execute_script('window.stop()')
except: except:
pass pass
if self.browser.current_url.startswith("data:"):
self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
time.sleep(2)
except NoSuchElementException: except NoSuchElementException:
self.print_and_log("Loop element not found: ", path) self.print_and_log("Loop element not found: ", path)
self.print_and_log("找不到循环元素: ", path) self.print_and_log("找不到循环元素: ", path)