Bitcoin Forum

require(RCurl)

last.page<-15640
num<-"00"
allposts=NULL
while(as.numeric(num)<=last.page){
  
  forum<-getURL(
    paste("https://bitcointalk.org/index.php?topic=85687.",num, sep=""),
    ssl.verifypeer = FALSE, useragent = "R"
  )
  
  
  forum<-readLines(tc <- textConnection(forum)); close(tc)
  dates1<-grep('<div class="smalltext">',forum)
  dates2<-dates1[seq(2,length(dates1),by=2)]
  forum2<-forum[dates2]
  if(length(grep("edit",forum2))>0){
    forum3<-forum2[-grep("edit",forum2)]
  }else{
    forum3<-forum2
  }
  
  dates=NULL
  for(i in 1:length(forum3)){
    temp<-unlist(strsplit(forum3[i],">"))
    date<-strsplit(temp[2],"</")[[1]][1]
    
    dates<-rbind(dates,date)
  }
  
  allposts<-rbind(allposts,dates)
  
  num<-20 + as.numeric(num)
  print(num)
}

rownames(allposts)<-1:length(allposts)

allposts<-allposts[-which(allposts=="<b")]

alldates=NULL
for(i in 1:length(allposts)){
  temp<-unlist(
    strsplit(
      unlist(strsplit(allposts[i],", ")),
      " "
    )
  )
  
  temp2<-cbind(temp[1],temp[2],temp[3])
  
  alldates<-rbind(alldates,temp2)
}
alldates<-as.data.frame(alldates)
alldates[,1]<-as.character(alldates[,1])
alldates[,2]<-as.numeric(as.character(alldates[,2]))
alldates[,3]<-as.numeric(as.character(alldates[,3]))



mnth<-month.name[1]
yr<-2012
counts=NULL

for(yr in c(2012,2013)){
  for(m in 1:length(month.name)){
    mnth<-month.name[m]
    temp<-alldates[which(alldates[,1]==mnth & alldates[,3]==yr),]
    if(nrow(temp)>0){
      
      
      for(i in 1:max(temp[,2])){
        cnt<-length(which(temp[,2]==i))
        
        counts.temp<-cbind(unique(temp[,1]),i,unique(temp[,3]),cnt)
        counts<-rbind(counts,counts.temp)
      }
      
    }
    
  }
  
}

counts<-as.data.frame(counts)
counts[,1]<-as.character(counts[,1])
counts[,2]<-as.numeric(as.character(counts[,2]))
counts[,3]<-as.numeric(as.character(counts[,3]))
counts[,4]<-as.numeric(as.character(counts[,4]))



x.vals<-round(seq(1,nrow(counts), length=10),0)
x.labs<-paste(counts[x.vals,1],counts[x.vals,2], counts[x.vals,3])

plot(counts[,4], type="l", lwd=2, col="Red",
     ylab="Number of Posts",xaxt="n", xlab="",
     main="Posts per Day in Wall Observer Thread"
)
axis(side=1, at=x.vals, labels=x.labs)

							<div class="post"><div class="quoteheader"><a href="https://bitcointalk.org/index.php?topic=85687.msg945087#msg945087">Quote from: proudhon on June 06, 2012, 05:38:47 PM</a></div><div class="quote"><div class="quoteheader"><a href="https://bitcointalk.org/index.php?topic=85687.msg945072#msg945072">Quote from: Piper67 on June 06, 2012, 05:31:01 PM</a></div><div class="quote"><div class="quoteheader"><a href="https://bitcointalk.org/index.php?topic=85687.msg945048#msg945048">Quote from: Spekulatius on June 06, 2012, 05:19:16 PM</a></div><div class="quote">a corresponding timesstamp would be nice<br /></div><br />Hmmm... aren&#039;t the messages on the forum time-stamped already?<br /></div><br />Yes, but he posted images that he&#039;d taken hours or days before he started the thread, I believe.<br /></div><br />yes the first 2 do not have a correct times stamp but are relatively new<br /><br />the time from the posts should be fine<div class="quoteheader"><a href="https://bitcointalk.org/index.php?topic=85687.msg945100#msg945100">Quote from: casascius on June 06, 2012, 05:49:37 PM</a></div><div class="quote">I wonder why turning on the &quot;show volume&quot; (the option that darkens the green line anywhere the volume spikes) isn&#039;t simply on by default.&nbsp; It&#039;s extra information at a cost of zero screen clutter.<br /></div><br />thanks i was forgetting about this option</div>