我在RStudio中运行了一个Web抓取脚本，得到了以下错误：
Selenium message:javascript error: this.each is not a function
(Session info: chrome=81.0.4044.129)
Build info: version: '4.0.0-alpha-2', revision: 'f148142cf8', time: '2019-07-01T21:30:10'
System info: host: 'xxxxxx', ip: 'xxx.xxx.x.xxx', os.name: 'Windows 10', os.arch: 'amd64', os.version: '10.0', java.version: '1.8.0_231'
Driver info: driver.version: unknown
Error: Summary: JavaScriptError
Detail: An error occurred while executing user supplied JavaScript.
class: org.openqa.selenium.JavascriptException
Further Details: run errorDetails method
我真的不明白问题出在哪里，也不知道该怎么解决。有人知道如何解决这个问题吗？我对此还很陌生，所以具体步骤对我来说非常实用。提前谢谢！
编辑：这是我正在使用的脚本。错误似乎发生在"主循环#结束"之前
library(data.table) # Required for rbindlist
library(dplyr) # Required to use the pipes %>% and some table manipulation commands
library(magrittr) # Required to use the pipes %>%
library(rvest) # Required for read_html
library(RSelenium) # Required for webscraping with javascript
library(lubridate) # Required to collect dates
library(stringr)
library(purrr)
options(stringsAsFactors = F) #needed to prevent errors when merging data frames
#Paste the GoodReads Url
url <- "https://www.goodreads.com/book/show/1885.Pride_and_Prejudice?ac=1&from_search=true&qid=VkA2NbcGBa&rank=1"
languageOnly = F #If FALSE, "all languages" is chosen
#Set your browser settings
rD <- rsDriver(port = 4585L, browser = "chrome", chromever = "81.0.4044.69")
remDr <- rD[["client"]]
remDr$setTimeout(type = "implicit", 2000)
remDr$navigate(url)
bookTitle = unlist(remDr$getTitle())
finalData = data.frame()
# Main loop going through the website pages
morePages = T
pageNumber = 1
while(morePages){
#Select reviews in correct language.
#It should also work if you only fill in the numeral language code, and leave the first one empty.
selectLanguage = if(languageOnly){
selectLanguage = remDr$findElement("xpath", "//select[@id='language_code']/option[@value='']")
} else {
selectLanguage = remDr$findElement("xpath", "//select[@id='language_code']/option[5]")
}
selectLanguage$clickElement()
Sys.sleep(3)
#Expand all reviews
expandMore <- remDr$findElements("link text", "...more")
sapply(expandMore, function(x) x$clickElement())
#Extracting the reviews from the page
reviews <- remDr$findElements("css selector", "#bookReviews .stacked")
reviews.html <- lapply(reviews, function(x){x$getElementAttribute("outerHTML")[[1]]})
reviews.list <- lapply(reviews.html, function(x){read_html(x) %>% html_text()} )
reviews.text <- unlist(reviews.list)
#Some reviews have only rating and no text, so we process them separately
onlyRating = unlist(map(1:length(reviews.text), function(i) str_detect(reviews.text[i], "^\n\n")))
#Full reviews
if(sum(!onlyRating) > 0){
filterData = reviews.text[!onlyRating]
fullReviews = purrr::map_df(seq(1, length(filterData), by=2), function(i){
review = unlist(strsplit(filterData[i], "n"))
data.frame(
date = mdy(review[2]), #date
username = str_trim(review[5]), #user
rating = str_trim(review[9]), #overall
comment = str_trim(review[12]) #comment
)
})
#Add review text to full reviews
fullReviews$review = unlist(purrr::map(seq(2, length(filterData), by=2), function(i){
str_trim(str_remove(filterData[i], "\s*\n\s*\(less\)"))
}))
} else {
fullReviews = data.frame()
}
#partial reviews (only rating)
if(sum(onlyRating) > 0){
filterData = reviews.text[onlyRating]
partialReviews = purrr::map_df(1:length(filterData), function(i){
review = unlist(strsplit(filterData[i], "n"))
data.frame(
date = mdy(review[9]), #date
username = str_trim(review[4]), #user
rating = str_trim(review[8]), #overall
comment = "",
review = ""
)
})
} else {
partialReviews = data.frame()
}
finalData = rbind(finalData, fullReviews, partialReviews)
#Go to next page if possible
nextPage = remDr$findElements("xpath", "//a[@class='next_page']")
if(length(nextPage) > 0){
message(paste("PAGE", pageNumber, "Processed - Going to next"))
nextPage[[1]]$clickElement()
pageNumber = pageNumber + 1
Sys.sleep(2)
} else {
message(paste("PAGE", pageNumber, "Processed - Last page"))
morePages = FALSE
}
}
#end of the main loop
#Replace missing ratings by 'not rated'
finalData$rating = ifelse(finalData$rating == "", "not rated", finalData$rating)
#Stop server
rD[["server"]]$stop()
#set directory to where you wish the file to go
#copy your working directory and exchange all backward slashes with forward slashes
getwd()
setwd("C:/Users/ledgreve/Desktop/GoodReads_TextMining-master/Scripts/New Scripts/Test1")
#Write results
write.csv(finalData, paste0(bookTitle, ".csv"), row.names = F)
message("FINISHED!")
只是我自己的更新：这个问题在我重新安装java并安装rjava后得到了解决(https://cimentadaj.github.io/blog/2018-05-25-installing-rjava-on-windows-10/installing-rjava-on-windows-10/)