spider/EasySpider
1
0
Fork 0
mirror of https://github.com/NaiboWang/EasySpider.git synced 2025-04-21 13:55:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Deal with data:

Browse Source
This commit is contained in:
naibo 2023-11-23 03:24:53 +08:00
parent 1e5ecf8874
commit d0822c805b
2 changed files with 5 additions and 1 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": ["--id", "[7]", "--read_type", "remote", "--headless", "0"] // "args": ["--id", "[7]", "--read_type", "remote", "--headless", "0"]
// "args": ["--id", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"] // "args": ["--id", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"]
"args": ["--id", "[119]", "--headless", "0", "--user_data", "0", "--keyboard", "0"] "args": ["--id", "[125]", "--headless", "0", "--user_data", "0", "--keyboard", "0"]
} }
] ]
} }

4
ExecuteStage/easyspider_executestage.py
View File

@ -1035,6 +1035,8 @@ class BrowserThread(Thread):
if self.browser.current_url.startswith("data:"): 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 self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
time.sleep(2) time.sleep(2)
elements = self.browser.find_elements(By.XPATH,
xpath, iframe=node["parameters"]["iframe"])
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"])
@ -1100,6 +1102,8 @@ class BrowserThread(Thread):
if self.browser.current_url.startswith("data:"): 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 self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
time.sleep(2) time.sleep(2)
elements = self.browser.find_elements(By.XPATH,
xpath, iframe=node["parameters"]["iframe"])
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)