How open and read pdf (originally .html) file using Python3

Question

I need to open this file in python3:

http://www.arch.gob.ec/index.php/descargas/doc_download/478-historial-de-produccion-nacional-de-crudo-2011.html

Here will I have to read it, and extract the data tables. I have searched for several hours but nothing seem to work. I am new to scraping/parsing and it is the first time I have looked in to file handling of PDF.

Thanks for all kind of help!

Answer 1

Found a way that works for me.

url = 'http://www.arch.gob.ec/index.php/descargas/doc_download/478-historial-de-produccion-nacional-de-crudo-2011.html'

(pdfFile, headers) = urllib.request.urlretrieve(url)
print(os.path.abspath(pdfFile))
s = pdf_convert(str(os.path.abspath(pdfFile)))

where pdf_convert is:

def pdf_convert(path):
outtype='txt'
opts={}
# Create file that that can be populated in Desktop
outfile = 'c:\\users\\yourusername\\Desktop\\temp2.txt'
outdir = '/'.join(path.split('/')[:-1])
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
# ?outfile = None
# ?outtype = None
outdir = None
#layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
showpageno = True
laparams = LAParams()
for (k, v) in opts:
    if k == '-d': debug += 1
    elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
    elif k == '-m': maxpages = int(v)
    elif k == '-P': password = v
    elif k == '-o': outfile = v
    elif k == '-n': laparams = None
    elif k == '-A': laparams.all_texts = True
    elif k == '-V': laparams.detect_vertical = True
    elif k == '-M': laparams.char_margin = float(v)
    elif k == '-L': laparams.line_margin = float(v)
    elif k == '-W': laparams.word_margin = float(v)
    elif k == '-F': laparams.boxes_flow = float(v)
    elif k == '-Y': layoutmode = v
    elif k == '-O': outdir = v
    elif k == '-t': outtype = v
    elif k == '-c': codec = v
    elif k == '-s': scale = float(v)
#
#PDFDocument.debug = debug
#PDFParser.debug = debug
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager()

outtype = 'text'

if outfile:
    outfp = open(outfile, 'w')

else:
    outfp = sys.stdout
device = TextConverter(rsrcmgr, outfp, laparams=laparams)


fp = open(path, 'rb')
process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
                check_extractable=True)
fp.close()
device.close()
outfp.close()
with open ('c:\\users\\studma~1\\Desktop\\temp2.txt', 'r') as myfile:
    data = myfile.read()
myfile.close()
return str(data)