Deal with data:

.temp_to_pub/EasySpider_windows_x64/execution_instances/135.json

@@ -0,0 +1 @@
+{"id":135,"name":"【软科排名】-中国最好学科排名|最权威的大学学科|高校学科排名","url":"https://www.shanghairanking.cn/rankings/bcsr/2023","links":"https://www.shanghairanking.cn/rankings/bcsr/2023","create_time":"2023/11/22 21:51:29","update_time":"2023/11/22 21:51:29","version":"0.5.0","saveThreshold":10,"cloudflare":0,"environment":0,"maxViewLength":15,"recordLog":1,"outputFormat":"xlsx","saveName":"current_time","inputExcel":"","startFromExit":0,"containJudge":false,"desc":"https://www.shanghairanking.cn/rankings/bcsr/2023","inputParameters":[{"id":0,"name":"urlList_0","nodeId":1,"nodeName":"打开网页","value":"https://www.shanghairanking.cn/rankings/bcsr/2023","desc":"要采集的网址列表，多行以\\n分开","type":"text","exampleValue":"https://www.shanghairanking.cn/rankings/bcsr/2023"},{"id":1,"name":"loopTimes_循环_1","nodeId":4,"nodeName":"循环","desc":"循环循环执行的次数（0代表无限循环）","type":"int","exampleValue":0,"value":0}],"outputParameters":[{"id":0,"name":"参数1_链接文本","desc":"","type":"text","recordASField":1,"exampleValue":"湖北大学\n "},{"id":1,"name":"参数3_文本","desc":"","type":"text","recordASField":1,"exampleValue":"（哲学）"}],"graph":[{"index":0,"id":0,"parentId":0,"type":-1,"option":0,"title":"root","sequence":[1,2],"parameters":{"history":1,"tabIndex":0,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0},"isInLoop":false},{"id":1,"index":1,"parentId":0,"type":0,"option":1,"title":"打开网页","sequence":[],"isInLoop":false,"position":0,"parameters":{"useLoop":false,"xpath":"","wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"url":"https://www.shanghairanking.cn/rankings/bcsr/2023","links":"https://www.shanghairanking.cn/rankings/bcsr/2023","maxWaitTime":10,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"cookies":""}},{"id":2,"index":2,"parentId":0,"type":1,"option":8,"title":"循环","sequence":[3,4],"isInLoop":false,"position":1,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"/html/body/div[1]/div[1]/div[1]/div[2]/div[2]/div[1]/div/div[2]/div/a[1]/span[2]","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"loopType":1,"pathList":"","textList":"","code":"","waitTime":0,"exitCount":0,"historyWait":2,"breakMode":0,"breakCode":"","breakCodeWaitTime":0,"allXPaths":""}},{"id":3,"index":3,"parentId":2,"type":0,"option":2,"title":"点击元素","sequence":[],"isInLoop":true,"position":0,"parameters":{"history":4,"tabIndex":-1,"useLoop":true,"xpath":"","iframe":false,"wait":2,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"clickWay":0,"maxWaitTime":10,"paras":[],"allXPaths":"","loopType":1}},{"id":4,"index":4,"parentId":2,"type":1,"option":8,"title":"循环","sequence":[6,5],"isInLoop":true,"position":1,"parameters":{"history":5,"tabIndex":-1,"useLoop":false,"xpath":"//*[contains(@class, \"ant-pagination-next\")]/a[1]","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"loopType":0,"pathList":"","textList":"","code":"","waitTime":0,"exitCount":0,"historyWait":2,"breakMode":0,"breakCode":"","breakCodeWaitTime":0,"allXPaths":["/html/body/div[1]/div[1]/div[1]/div[2]/div[1]/div[3]/div[2]/div[1]/div[1]/ul[1]/li[5]/a[1]","//a[contains(., '')]","//A[@class='ant-pagination-item-link']","/html/body/div[last()-3]/div/div/div[last()-2]/div/div/div/div[last()-1]/div/ul/li[last()-1]/a"]}},{"id":6,"index":5,"parentId":4,"type":0,"option":2,"title":"点击元素","sequence":[],"isInLoop":true,"position":1,"parameters":{"history":5,"tabIndex":-1,"useLoop":true,"xpath":"","iframe":false,"wait":2,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"clickWay":0,"maxWaitTime":10,"paras":[],"allXPaths":["/html/body/div[1]/div[1]/div[1]/div[2]/div[1]/div[3]/div[2]/div[1]/div[1]/ul[1]/li[5]/a[1]","//a[contains(., '')]","//A[@class='ant-pagination-item-link']","/html/body/div[last()-3]/div/div/div[last()-2]/div/div/div/div[last()-1]/div/ul/li[last()-1]/a"],"loopType":0}},{"id":5,"index":6,"parentId":4,"type":1,"option":8,"title":"循环","sequence":[8,7],"isInLoop":true,"position":0,"parameters":{"history":5,"tabIndex":-1,"useLoop":false,"xpath":"/html/body/div[1]/div[1]/div[1]/div[2]/div[1]/div[3]/div[2]/div[1]/div[1]/div[2]/table[1]/tbody[1]/tr/td[4]/div[1]/div[2]/div[1]/div[1]/div[1]/a[1]","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"loopType":1,"pathList":"","textList":"","code":"","waitTime":0,"exitCount":0,"historyWait":2,"breakMode":0,"breakCode":"","breakCodeWaitTime":0,"allXPaths":["/html/body/div[1]/div[1]/div[1]/div[2]/div[1]/div[3]/div[2]/div[1]/div[1]/div[2]/table[1]/tbody[1]/tr[1]/td[4]/div[1]/div[2]/div[1]/div[1]/div[1]/a[1]","//a[contains(., '湖北大学')]","//A[@class='name-cn']","/html/body/div[last()-3]/div/div/div[last()-1]/div/div/div/div[last()-1]/div/div[last()-1]/table/tbody/tr[last()-29]/td[last()-1]/div/div/div[last()-1]/div/div/a"]}},{"id":8,"index":7,"parentId":5,"type":0,"option":3,"title":"提取数据","sequence":[],"isInLoop":true,"position":1,"parameters":{"history":5,"tabIndex":-1,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"clear":0,"paras":[{"nodeType":1,"contentType":0,"relative":true,"name":"参数1_链接文本","desc":"","extractType":0,"relativeXPath":"","allXPaths":"","exampleValues":[{"num":0,"value":"湖北大学\n "}],"unique_index":"dgby6tuc79nlp9toe7t","iframe":false,"default":"","paraType":"text","recordASField":1,"beforeJS":"","beforeJSWaitTime":0,"JS":"","JSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"downloadPic":0}],"loopType":1}},{"id":7,"index":8,"parentId":5,"type":0,"option":3,"title":"提取数据","sequence":[],"isInLoop":true,"position":0,"parameters":{"history":5,"tabIndex":-1,"useLoop":false,"xpath":"","iframe":false,"wait":0,"waitType":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"waitElement":"","waitElementTime":10,"waitElementIframeIndex":0,"clear":0,"paras":[{"nodeType":0,"contentType":0,"relative":false,"name":"参数3_文本","desc":"","extractType":0,"relativeXPath":"/html/body/div[1]/div[1]/div[1]/div[2]/div[1]/div[3]/div[2]/div[1]/div[1]/div[1]/div[1]/div[3]","allXPaths":["/html/body/div[1]/div[1]/div[1]/div[2]/div[1]/div[3]/div[2]/div[1]/div[1]/div[1]/div[1]/div[3]","//div[contains(., '（哲学）')]","/html/body/div[last()-3]/div/div/div[last()-1]/div/div/div/div[last()-1]/div/div[last()-2]/div[last()-1]/div[last()-1]"],"exampleValues":[{"num":0,"value":"（哲学）"}],"unique_index":"xgoa18n26rllp9toqoa","iframe":false,"default":"","paraType":"text","recordASField":1,"beforeJS":"","beforeJSWaitTime":0,"JS":"","JSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"downloadPic":0}]}}]}

ExecuteStage/easyspider_executestage.py

@@ -894,6 +894,7 @@ def loopExecute(self, node, loopValue, clickPath="", index=0):
  thisHistoryLength = 0
  self.history["index"] = thisHistoryLength
  self.history["handle"] = thisHandle
+ thisHitoryURL = self.browser.current_url
  if int(node["parameters"]["loopType"]) == 0: # 单个元素循环
  # 无跳转标签页操作
  count = 0 # 执行次数
@@ -1033,14 +1034,19 @@ def loopExecute(self, node, loopValue, clickPath="", index=0):
  self.browser.execute_script('window.stop()')
  except:
  pass
+ ti = 0
  if self.browser.current_url.startswith("data:"):
- try:
- self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
- except: # 超时的情况下
- pass
+ while self.browser.current_url != thisHitoryURL: # 如果执行完一次循环之后网址发生了变化
+ try:
+ self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
+ except: # 超时的情况下
+ pass
+ ti += 1
+ if self.browser.current_url == thisHitoryURL or ti > thisHistoryLength: # 如果执行完一次循环之后网址发生了变化
+ break
  time.sleep(2)
  elements = self.browser.find_elements(By.XPATH,
-  xpath, iframe=node["parameters"]["iframe"])
+ xpath, iframe=node["parameters"]["iframe"])
  if index > 0:
  index -= 1 # 如果是data:开头的网址，就要重试一次
  if int(node["parameters"]["breakMode"]) > 0: # 如果设置了退出循环的脚本条件
@@ -1110,14 +1116,29 @@ def loopExecute(self, node, loopValue, clickPath="", index=0):
  self.browser.execute_script('window.stop()')
  except:
  pass
+ # if self.browser.current_url.startswith("data:"):
+ # try:
+ # self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
+ # except: # 超时的情况下
+ # pass
+ # time.sleep(2)
+ # elements = self.browser.find_elements(By.XPATH,
+ # xpath, iframe=node["parameters"]["iframe"])
+ # if index > 0:
+ # index -= 1 # 如果是data:开头的网址，就要重试一次
+ ti = 0
  if self.browser.current_url.startswith("data:"):
- try:
- self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
- except: # 超时的情况下
- pass
+ while self.browser.current_url != thisHitoryURL: # 如果执行完一次循环之后网址发生了变化
+ try:
+ self.browser.execute_script("history.go(1)") # 如果是data:开头的网址，就前进一步
+ except: # 超时的情况下
+ pass
+ ti += 1
+ if self.browser.current_url == thisHitoryURL or ti > thisHistoryLength: # 如果执行完一次循环之后网址发生了变化
+ break
  time.sleep(2)
  elements = self.browser.find_elements(By.XPATH,
-  xpath, iframe=node["parameters"]["iframe"])
+ xpath, iframe=node["parameters"]["iframe"])
  if index > 0:
  index -= 1 # 如果是data:开头的网址，就要重试一次
  except NoSuchElementException: