Question

R 抓取网页怎么能一次抓取完第一页之后“下一页”的内容

Answer 1

一般在页面代码里能看到下一页的链接或者信息，然后你可以直接引用或者组合，下面是我写过的一个很简单的例子，你可以看下。
library(rvest)
library(base)
library(XML)

start_url <- "http://movie.douban.com/subject/6126442/comments"

x <- data.frame(review="")
x$review<- as.character(x$review)

#initial condition startup
condition="hello"
review_count=0

while(length(condition)>0)
{
page <- html(start_url)
review <- html_nodes(page, "#comments p")
for(i in 1:length(review)){
x[review_count+i, 1]=as.character(html_text(review[i]))
}

table_urls <- page %>%
html_nodes(".next") %>%
html_attr("href") %>%
XML::getRelativeURL(start_url)
good <- as.character(table_urls)
bad <- substr(good,start = 41,stop = 96)

start_url <- paste("http://movie.douban.com/subject/6126442/comments", bad, sep="")
review_count=review_count+length(review)
condition <- as.character(html_text(html_nodes(page, ".next")))
}