R语言rvest爬取

rm(list = ls())


# 加载包
library('xml2')
library('rvest')






#广东省爬取
web<-read_html("http://www.agri.com.cn/company/township_city_index.asp?province_id=440000",
               encoding="gb2312")




#广东省城市链接获取
position<-web %>% html_nodes("a") %>% html_attr('href')


test1 <- data.frame(position)


test2 <- data.frame(test1[19:39,])


colnames(test2) <- c('urls')


test2$urls <- as.character(test2$urls)




n1 <- nrow(test2)


binddata <- data.frame(1)


colnames(binddata) <- c('phone1')






for(i in 1:n1){
#获取第一个城市链接
url1 <- test2$urls[i]


web1 <- read_html(url1,encoding = 'gb2312')


position1 <-web1 %>% html_nodes("a") %>% html_attr('href')






test11 <- data.frame(position1)


colnames(test11) <- c('urls')






#获取第一个城市下,所有城镇乡村电话
test11$urlsbz <- grepl(pattern = '/town/',test11$urls)


test22 <- test11$urls[which(test11$urlsbz == TRUE)]


test22 <- data.frame(test22)


colnames(test22) <- c('urls')


test22$urls <- as.character(test22$urls)




n2 <- nrow(test22)


for(j in 1:n2){


#第一个乡村界面
url1_1 <- test22$urls[j]


web1_1 <- read_html(url1_1,encoding = 'gbk')






position2 <- web1_1 %>% html_nodes("a") %>% html_attr('href')




test33 <- data.frame(position2)


colnames(test33) <- c('urls')


test33$urls <- as.character(test33$urls)






#获取出电话url
num1 <- grep(pattern = '/tel/',test33$urls)


url1_2 <- test33$urls[num1]




#电话url进行调转
web1_2 <- read_html(url1_2,encoding = 'gbk')






phone1 <- web1_2 %>% 
  html_nodes(css = 'tr:nth-child(2)') %>% html_text()




phone1 <- data.frame(phone1)




phone1$phone1 <- as.character(phone1$phone1)


binddata <- rbind(binddata,phone1$phone1[6])