我在抓网站的时候大概10个网页成功以后就会提示这个问题
Python用的是3.4.3,Requests用的是2.7.0.
import requests
from bs4 import BeautifulSoup
import os.path
s = requests.session()
login_data = {'dest': '/','user': '******', 'pass': '******'}
header_info={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0'}
url='http://www.oxfordreference.com/LOGIN'
s.post(url,data=login_data,headers=header_info)
for i in range(1,100):
downprefix='http://www.oxfordreference.com/view/10.1093/acref/9780198294818.001.0001/acref-9780198294818-e-'
downurl=downprefix+str(i)
r=s.get(downurl,headers=header_info,timeout=30)
if r.status_code==200:
soup=BeautifulSoup(r.content,"html.parser")
shorten=str(soup.find_all("p", class_="entryContent"))
fname='acref-9780198294818-e-'+str(i)+'.htm'
newname=os.path.join('shorten',fname)
htmfile=open(newname,'w',encoding="utf_8")
htmfile.write(shorten)
htmfile.close()
print('Success in '+str(i))
else:
print('Error in '+str(i))
errorfile=open('errors.txt','a',encoding="utf_8")
errorfile.write(str(i))
errorfile.write('\n')
errorfile.close()
完整的traceback是这样的:
Traceback (most recent call last):
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\connectionpool.py", line 372, in makerequest
httplib_response = conn.getresponse(buffering=True)
TypeError: getresponse() got an unexpected keyword argument 'buffering'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\connectionpool.py", line 544, in urlopen
body=body, headers=headers)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\connectionpool.py", line 374, in makerequest
httplib_response = conn.getresponse()
File "D:\Program Files (x86)\python343\lib\http\client.py", line 1171, in getresponse
response.begin()
File "D:\Program Files (x86)\python343\lib\http\client.py", line 351, in begin
version, status, reason = self._read_status()
File "D:\Program Files (x86)\python343\lib\http\client.py", line 321, in readstatus
raise BadStatusLine(line)
http.client.BadStatusLine: ''
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\Program Files (x86)\python343\lib\site-packages\requests\adapters.py", line 370, in send
timeout=timeout
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\connectionpool.py", line 597, in urlopen
_stacktrace=sys.exc_info()[2])
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\util\retry.py", line 245, in increment
raise six.reraise(type(error), error, _stacktrace)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\packages\six.py", line 309, in reraise
raise value.with_traceback(tb)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\connectionpool.py", line 544, in urlopen
body=body, headers=headers)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\packages\urllib3\connectionpool.py", line 374, in makerequest
httplib_response = conn.getresponse()
File "D:\Program Files (x86)\python343\lib\http\client.py", line 1171, in getresponse
response.begin()
File "D:\Program Files (x86)\python343\lib\http\client.py", line 351, in begin
version, status, reason = self._read_status()
File "D:\Program Files (x86)\python343\lib\http\client.py", line 321, in readstatus
raise BadStatusLine(line)
requests.packages.urllib3.exceptions.ProtocolError: ('Connection aborted.', BadStatusLine("''",))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\stuff\Mdict\dict by me\odoa\newahktest\CrawlTest2.py", line 14, in <module>
r=s.get(downurl,headers=header_info,timeout=30) #100s wait
File "D:\Program Files (x86)\python343\lib\site-packages\requests\sessions.py", line 477, in get
return self.request('GET', url, **kwargs)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\sessions.py", line 465, in request
resp = self.send(prep, **send_kwargs)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\sessions.py", line 573, in send
r = adapter.send(request, **kwargs)
File "D:\Program Files (x86)\python343\lib\site-packages\requests\adapters.py", line 415, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', BadStatusLine("''",))
으아아아