Sat 25 Apr 2009 05:39:37 PM UTC, comment #3:
Same problem here... as of yet I couldn't even reach 1.0MB of data. It crashed after lastfm_dump.txt reached exact 10800 lines (or 10800 songs), file size: 563898 bytes.
My last.fm username is the same as here.
My lastest try:
Paco de Lucía Recuerdo a Patiño (Alegrías) 2008-08-16T07:46:52Z
Paco de Lucía Llanto a Cadiz (Tientos) 2008-08-16T07:43:24Z
Paco de Lucía Gitanos Trianeros (Soleá) 2008-08-16T07:39:42Z
Traceback (most recent call last):
File "./lastscrape.py", line 70, in <module>
sys.exit(main(*sys.argv))
File "./lastscrape.py", line 61, in main
for artist, track, timestamp in fetch_tracks(args[1]):
File "./lastscrape.py", line 47, in fetch_tracks
for artist, track, timestamp in tracks:
File "./lastscrape.py", line 14, in parse_page
soup = BeautifulSoup(urllib2.urlopen(page), convertEntities=BeautifulSoup.HTML_ENTITIES)
File "/usr/lib/python2.5/urllib2.py", line 124, in urlopen
return _opener.open(url, data)
File "/usr/lib/python2.5/urllib2.py", line 387, in open
response = meth(req, response)
File "/usr/lib/python2.5/urllib2.py", line 498, in http_response
'http', request, response, code, msg, hdrs)
File "/usr/lib/python2.5/urllib2.py", line 419, in error
result = self._call_chain(*args)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 582, in http_error_302
return self.parent.open(new)
File "/usr/lib/python2.5/urllib2.py", line 381, in open
response = self._open(req, data)
File "/usr/lib/python2.5/urllib2.py", line 399, in _open
'_open', req)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 1107, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.5/urllib2.py", line 1080, in do_open
r = h.getresponse()
File "/usr/lib/python2.5/httplib.py", line 928, in getresponse
response.begin()
File "/usr/lib/python2.5/httplib.py", line 385, in begin
version, status, reason = self._read_status()
File "/usr/lib/python2.5/httplib.py", line 349, in _read_status
raise BadStatusLine(line)
httplib.BadStatusLine
|
Thu 23 Apr 2009 05:47:56 PM UTC, comment #2:
I am having the same problem on Intrepid with the same version of python-beautifulsoup. I tried it 3 times at different times of the day as instructed: ./lastscrape.py larryni lastfm_dump.txt
It doesn't seem to be a particular artist/track/timestamp that causes it. The first time it pulled 6.3MB of data, then 1.1MB, and finally 4.8MB.
Here's the 3 tracebacks:
Attempt 1:
Traceback (most recent call last):
File "./lastscrape.py", line 71, in <module>
sys.exit(main(*sys.argv))
File "./lastscrape.py", line 63, in main
for artist, track, timestamp in fetch_tracks(args[1]):
File "./lastscrape.py", line 47, in fetch_tracks
for artist, track, timestamp in tracks:
File "./lastscrape.py", line 14, in parse_page
soup = BeautifulSoup(urllib2.urlopen(page))
File "/usr/lib/python2.5/urllib2.py", line 124, in urlopen
return _opener.open(url, data)
File "/usr/lib/python2.5/urllib2.py", line 387, in open
response = meth(req, response)
File "/usr/lib/python2.5/urllib2.py", line 498, in http_response
'http', request, response, code, msg, hdrs)
File "/usr/lib/python2.5/urllib2.py", line 419, in error
result = self._call_chain(*args)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 582, in http_error_302
return self.parent.open(new)
File "/usr/lib/python2.5/urllib2.py", line 381, in open
response = self._open(req, data)
File "/usr/lib/python2.5/urllib2.py", line 399, in _open
'_open', req)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 1107, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.5/urllib2.py", line 1080, in do_open
r = h.getresponse()
File "/usr/lib/python2.5/httplib.py", line 928, in getresponse
response.begin()
File "/usr/lib/python2.5/httplib.py", line 385, in begin
version, status, reason = self._read_status()
File "/usr/lib/python2.5/httplib.py", line 349, in _read_status
raise BadStatusLine(line)
httplib.BadStatusLine
Attempt 2:
Traceback (most recent call last):
File "./lastscrape.py", line 71, in <module>
sys.exit(main(*sys.argv))
File "./lastscrape.py", line 63, in main
for artist, track, timestamp in fetch_tracks(args[1]):
File "./lastscrape.py", line 47, in fetch_tracks
for artist, track, timestamp in tracks:
File "./lastscrape.py", line 14, in parse_page
soup = BeautifulSoup(urllib2.urlopen(page))
File "/usr/lib/python2.5/urllib2.py", line 124, in urlopen
return _opener.open(url, data)
File "/usr/lib/python2.5/urllib2.py", line 387, in open
response = meth(req, response)
File "/usr/lib/python2.5/urllib2.py", line 498, in http_response
'http', request, response, code, msg, hdrs)
File "/usr/lib/python2.5/urllib2.py", line 419, in error
result = self._call_chain(*args)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 582, in http_error_302
return self.parent.open(new)
File "/usr/lib/python2.5/urllib2.py", line 381, in open
response = self._open(req, data)
File "/usr/lib/python2.5/urllib2.py", line 399, in _open
'_open', req)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 1107, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.5/urllib2.py", line 1080, in do_open
r = h.getresponse()
File "/usr/lib/python2.5/httplib.py", line 928, in getresponse
response.begin()
File "/usr/lib/python2.5/httplib.py", line 385, in begin
version, status, reason = self._read_status()
File "/usr/lib/python2.5/httplib.py", line 349, in _read_status
raise BadStatusLine(line)
httplib.BadStatusLine
Attempt 3:
Traceback (most recent call last):
File "./lastscrape.py", line 71, in <module>
sys.exit(main(*sys.argv))
File "./lastscrape.py", line 63, in main
for artist, track, timestamp in fetch_tracks(args[1]):
File "./lastscrape.py", line 47, in fetch_tracks
for artist, track, timestamp in tracks:
File "./lastscrape.py", line 14, in parse_page
soup = BeautifulSoup(urllib2.urlopen(page))
File "/usr/lib/python2.5/urllib2.py", line 124, in urlopen
return _opener.open(url, data)
File "/usr/lib/python2.5/urllib2.py", line 381, in open
response = self._open(req, data)
File "/usr/lib/python2.5/urllib2.py", line 399, in _open
'_open', req)
File "/usr/lib/python2.5/urllib2.py", line 360, in _call_chain
result = func(*args)
File "/usr/lib/python2.5/urllib2.py", line 1107, in http_open
return self.do_open(httplib.HTTPConnection, req)
File "/usr/lib/python2.5/urllib2.py", line 1082, in do_open
raise URLError(err)
urllib2.URLError: <urlopen error (-2, 'Name or service not known')>
If you want I can send you the 3 lastfm_dump.txt files as well, they are too large to attach here.
|