http=require'socket.http'
--iterator1 = io.lines("uniq.txt")
start_topic=0
end_topic=20000
urlbit1="http://www.volvo300mania.com/fr/forum/viewtopic.php?t="
urlbit2="&start="
urlbit3="&view=print"
for topic=start_topic,end_topic do
--for topic in iterator1 do
old_url_text_length=0
saved_pages=""
for start_page=0, 15000, 15 do
url=urlbit1..topic..urlbit2..start_page..urlbit3
url_text, statusCode, headers, statusText = http.request(url)
if statusCode ~=200 then
print("Topic "..topic.." does not exist.")
break
end
worked_OK, url_text_length=pcall(string.len,url_text)
if not worked_OK then print("Error getting length of text for topic: "..topic) break
elseif start_page==0 then print("New topic: "..topic)
elseif url_text_length==old_url_text_length then
print("Reached end of this topic.")
break
end
old_url_text_length=url_text_length
newfile=topic.."_"..start_page..".pdf"
wkhtmltopdf_string="wkhtmltopdf ".."\""..url.."\" "..newfile
--print(wkhtmltopdf_string)
if pcall(os.execute, wkhtmltopdf_string)
then
print("Saved: "..newfile)
saved_pages=saved_pages..newfile.." "
else
print("Error converting topic: "..topic.." to pdf.")
end
end
combined_file=topic..".pdf"
_, count = string.gsub(saved_pages, ".pdf ", ".pdf ")
if count>0 then
print("Saved pages: "..saved_pages)
end
if count>1 then
pcall(os.execute, "pdfunite "..saved_pages..combined_file)
print("Combined as: "..combined_file)
pcall(os.execute, "rm "..saved_pages)
print("Removed originals: "..saved_pages)
elseif count==1 then
pcall(os.execute, "mv "..saved_pages..combined_file)
print("Renamed original: "..saved_pages.." to: "..combined_file)
end
end