替代解决方案

Question

我正在尝试在RSelenium中实现异常处理，请寻求帮助。请注意，我已经检查了使用robotstxt软件包抓取此页面的权限。

library(RSelenium)
library(XML)
library(janitor)
library(lubridate)
library(magrittr)
library(dplyr)

remDr <- remoteDriver(
  remoteServerAddr = "192.168.99.100",
  port = 4445L
)
remDr$open()

# Open TightVNC to follow along as RSelenium drives the browser

# navigate to the main page
remDr$navigate("https://docs.google.com/spreadsheets/d/1o1PlLIQS8v-XSuEz1eqZB80kcJk9xg5lsbueB7mTg1U/pub?output=html&widget=true#gid=690408156")

# look for table element
tableElem <- remDr$findElement(using = "id", "pageswitcher-content")

# switch to table
remDr$switchToFrame(tableElem)

# parse html for first table
doc <- htmlParse(remDr$getPageSource()[[1]])
table_tmp <- readHTMLTable(doc)
table_tmp <- table_tmp[[1]][-2, -1]
table_tmp <- table_tmp[-1, ]
colnames(table_tmp) <- c("team_name", "team_size", "start_time", "end_time", "total_time", "puzzels_solved")
table_tmp$city <- rep("montreal", nrow(table_tmp))
table_tmp$date <- rep(Sys.Date() - 5, nrow(table_tmp))

# switch back to the main/outer frame
remDr$switchToFrame(NULL)

# I found the elements I want to manipulate with Inspector mode in a browser
webElems <- remDr$findElements(using = "css", ".switcherItem") # Month/Year tabs at the bottom
arrowElems <- remDr$findElements(using = "css", ".switcherArrows") # Arrows to scroll left and right at the bottom

# Create NULL object to be used in for loop
big_df <- NULL
for (i in seq(length(webElems))) {

  # choose the i'th Month/Year tab
  webElem <- webElems[[i]]
  webElem$clickElement()

  tableElem <- remDr$findElement(using = "id", "pageswitcher-content") # The inner table frame

  # switch to table frame
  remDr$switchToFrame(tableElem)
  Sys.sleep(3)
  # parse html with XML package
  doc <- htmlParse(remDr$getPageSource()[[1]])
  Sys.sleep(3)
  # Extract data from HTML table in HTML document
  table_tmp <- readHTMLTable(doc)
  Sys.sleep(3)
  # put this into a format you can use
  table <- table_tmp[[1]][-2, -1]
  table <- table[-1, ]
  # rename the columns
  colnames(table) <- c("team_name", "team_size", "start_time", "end_time", "total_time", "puzzels_solved")
  # add city name to a column
  table$city <- rep("Montreal", nrow(table))

  # add the Month/Year this table was extracted from
  today <- Sys.Date() %m-% months(i + 1)
  table$date <- today

  # concatenate each table together
  big_df <- dplyr::bind_rows(big_df, table)

  # Switch back to main frame
  remDr$switchToFrame(NULL)

  ################################################
  ###   I should use exception handling here   ###
  ################################################


}

当浏览器进入January 2018表时，它不再能够找到下一个webElems元素并抛出并出错：

Selenium message：元素当前不可见，因此可能无法与之交互   内部版本信息：版本：'2.53.1'，版本：'a36b8b1'，时间：'2016-06-30 17:37:03'   系统信息：主机：'617e51cbea11'，ip：'172.17.0.2'，os.name：'Linux'，os.arch：'amd64'，os.version：'4.14.79-boot2docker'，java.version：' 1.8.0_91'   驱动程序信息：driver.version：未知

错误：摘要：ElementNotVisible   详细信息：元素命令无法完成，因为该元素在页面上不可见。   类：org.openqa.selenium.ElementNotVisibleException   更多详细信息：运行errorDetails方法   另外：有50个或更多警告（请使用warnings（）查看前50个警告）

我一直在天真地处理它，方法是在for循环的末尾包含此代码。这不是一个好主意，原因有两个：1）难以确定滚动速度，并且在其他（较长）的Google页面上可能会失败，2）for循环最终在尝试单击向右箭头时最终失败已经结束了-因此它将不会下载最后几张表。

# click the right arrow to scroll right
arrowElem <- arrowElems[[1]]
# once you "click"" the element it is "held down" - no way to " unclick" to prevent it from scrolling too far
# I currently make sure it only scrolls a short distance - via Sys.sleep() before switching to outer frame
arrowElem$clickElement()
# give it "just enough time" to scroll right
Sys.sleep(0.3)
# switch back to outer frame to re-start the loop
remDr$switchToFrame(NULL)

我想发生的是，当此错误弹出时，通过执行arrowElem$clickElement()处理此异常。我认为通常会使用tryCatch()；但是，这也是我第一次学习有关异常处理的知识。我以为可以将其包含在for循环的remDr$switchToFrame(tableElem)部分中，但不起作用：

tryCatch({
        suppressMessages({
            remDr$switchToFrame(tableElem)
        })
    },
    error = function(e) {
        arrowElem <- arrowElems[[1]]
        arrowElem$clickElement()
        Sys.sleep(0.3)
        remDr$switchToFrame(NULL)
    }
)

Answer 1

我尝试了一下。处理异常时，我喜欢使用某种形式的

check <- try(expression, silent = TRUE) # or suppressMessages(try(expression, silent = TRUE))
if (any(class(check) == "try-error")) {
  # do stuff
}

我发现它使用方便，并且通常可以正常工作，包括使用硒时。但是，这里遇到的问题是，一旦单击箭头，总会把我带到最后个可见的页面-跳过中间的所有内容。

替代解决方案

因此，这是一个替代方案，可以解决废弃表 不上述意义上的异常处理任务。

代码

# Alernative: -------------------------------------------------------------

remDr <- RSelenium::remoteDriver(
  remoteServerAddr = "192.168.99.100",
  port = 4445L
)
remDr$open(silent = TRUE)
# navigate to the main page
# needs no be done once before looping, else content is not available
remDr$navigate("https://docs.google.com/spreadsheets/d/1o1PlLIQS8v-XSuEz1eqZB80kcJk9xg5lsbueB7mTg1U/pub?output=html&widget=true#gid=690408156")


# I. Preliminaries:
# 
# 1. build the links to all spreadsheets
# 2. define the function create_table
# 
# 1.
# get page source
html <- remDr$getPageSource()[[1]]
# split it line by line
html <- unlist(strsplit(html, '\n'))
# restrict to script section
script <- grep('^\\s*var\\s+gidMatch', html, value = TRUE)
# split the script by semi-colon
script <- unlist(strsplit(script, ';'))
# retrieve information
sheet_months <- gsub('.*name:.{2}(.*?).{1},.*', '\\1', 
                     grep('\\{name\\s*\\:', script, value = TRUE), perl = TRUE)
sheet_gid <- gsub('.*gid:.{2}(.*?).{1},.*', '\\1', 
                  grep('\\gid\\s*\\:', script, value = TRUE), perl = TRUE)
sheet_url <- paste0('https://docs.google.com/spreadsheets/d/1o1PlLIQS8v-XSuEz1eqZB80kcJk9xg5lsbueB7mTg1U/pubhtml/sheet?headers%5Cx3dfalse&gid=',
                    sheet_gid)
#
# 2. 
# table yielding function
# just for readability in the loop
create_table <- function (remDr) {
  # parse html with XML package
  doc <- XML::htmlParse(remDr$getPageSource()[[1]])
  Sys.sleep(3)
  # Extract data from HTML table in HTML document
  table_tmp <- XML::readHTMLTable(doc)
  Sys.sleep(3)
  # put this into a format you can use
  table <- table_tmp[[1]][-2, -1]
  # add a check-up for size mismatch
  table_fields <- as.character(t(table[1,]))
  if (! any(grepl("size", tolower(table_fields)))) {
    table <- table[-1, ]
    # rename the columns
    colnames(table) <- c("team_name", "start_time", "end_time", "total_time", "puzzels_solved")
    table$team_size <- NA_integer_
    table <- table[,c("team_name", "team_size", "start_time", "end_time", "total_time", "puzzels_solved")]
  } else {
    table <- table[-1, ]
    # rename the columns
    colnames(table) <- c("team_name", "team_size", "start_time", "end_time", "total_time", "puzzels_solved")
  }
  # add city name to a column
  table$city <- rep("Montreal", nrow(table))

  # add the Month/Year this table was extracted from
  today <- Sys.Date()
  lubridate::month(today) <- lubridate::month(today)+1
  table$date <- today

  # returns the table
  table
}

# II. Scrapping the content
# 
# 1. selenium to generate the pages
# 2. use create_table to extract the table
# 
big_df <- NULL
for (k in seq_along(sheet_url)) {
  # 1. navigate to the page
  remDr$navigate(sheet_url[k])
  # remDr$screenshot(display = TRUE) maybe one wants to see progress
  table <- create_table(remDr)

  # 2. concatenate each table together
  big_df <- dplyr::bind_rows(big_df, table)

  # inform progress 
  cat(paste0('\nGathered table for: \t', sheet_months[k]))
}

# close session
remDr$close()

结果

在这里您可以看到head的{{1}}和tail

big_df

简短说明

要执行此任务，我要做的是首先生成指向文档中所有电子表格的链接。为此：
- 浏览文档一次
- 提取源代码
- 使用head(big_df) # team_name team_size start_time end_time total_time puzzels_solved city date # 1 Tortoise Tortes 5 19:00 20:05 1:05 5 Montreal 2019-02-20 # 2 Mulholland Drives Over A Smelly Cat 4 7:25 8:48 1:23 5 Montreal 2019-02-20 # 3 B.R.O.O.K. 2 7:23 9:05 1:42 5 Montreal 2019-02-20 # 4 Motivate 4 18:53 20:37 1:44 5 Montreal 2019-02-20 # 5 Fighting Mongooses 3 6:31 8:20 1:49 5 Montreal 2019-02-20 # 6 B Lovers 3 6:40 8:30 1:50 5 Montreal 2019-02-20 tail(big_df) # team_name team_size start_time end_time total_time puzzels_solved city date # 545 Ale Mary <NA> 6:05 7:53 1:48 5 Montreal 2019-02-20 # 546 B.R.O.O.K. <NA> 18:45 20:37 1:52 5 Montreal 2019-02-20 # 547 Ridler Co. <NA> 6:30 8:45 2:15 5 Montreal 2019-02-20 # 548 B.R.O.O.K. <NA> 18:46 21:51 3:05 5 Montreal 2019-02-20 # 549 Rotating Puzzle Collective <NA> 18:45 21:51 3:06 5 Montreal 2019-02-20 # 550 Fire Team <NA> 19:00 22:11 3:11 5 Montreal 2019-02-20提取工作表月份和URL（通过gid数字）
完成后，遍历Urls，收集并绑定表

出于可读性考虑，我创建了一个名为regex的小函数，该函数以正确的格式返回表。它主要是循环中包含的代码。我仅对列数添加了安全措施（某些电子表格没有create_table字段-在那些情况下，我将其设置为team_size）。

异常处理RSelenium switchToFrame（）错误：ElementNotVisible

1 个答案:

替代解决方案