我在Python 2.7中编写了一个简单的脚本，它使用urllib（2），cookielib和bs4编译我的学校网站上的作业。当我从我的IDE运行它时，它完美无误地运行。但是当为Alexa编译它并在AWS Lambda上运行它时，我收到以下错误：
[Errno 104] Connection reset by peer: error
Traceback (most recent call last):
File "/var/task/lambda_function.py", line 136, in lambda_handler
return on_launch(event['request'], event['session'])
File "/var/task/lambda_function.py", line 80, in on_launch
return scraper(session)
File "/var/task/lambda_function.py", line 98, in scraper
open(URL)
File "/var/task/lambda_function.py", line 16, in open
return browser.open(url, postdata).read()
File "/usr/lib64/python2.7/urllib2.py", line 429, in open
response = self._open(req, data)
File "/usr/lib64/python2.7/urllib2.py", line 447, in _open
'_open', req)
File "/usr/lib64/python2.7/urllib2.py", line 407, in _call_chain
result = func(*args)
File "/usr/lib64/python2.7/urllib2.py", line 1243, in https_open
context=self._context)
File "/usr/lib64/python2.7/urllib2.py", line 1203, in do_open
r = h.getresponse(buffering=True)
File "/usr/lib64/python2.7/httplib.py", line 1136, in getresponse
response.begin()
File "/usr/lib64/python2.7/httplib.py", line 453, in begin
version, status, reason = self._read_status()
File "/usr/lib64/python2.7/httplib.py", line 409, in _read_status
line = self.fp.readline(_MAXLINE + 1)
File "/usr/lib64/python2.7/socket.py", line 480, in readline
data = self._sock.recv(self._rbufsize)
File "/usr/lib64/python2.7/ssl.py", line 756, in recv
return self.read(buflen)
File "/usr/lib64/python2.7/ssl.py", line 643, in read
v = self._sslobj.read(len)
error: [Errno 104] Connection reset by peer
我知道通常这是因为我试图访问的服务器正在丢弃连接，但我无法弄清楚它为什么在我的IDE中运行而不是在我的lambda中。
这是我在IDE中使用的原始代码：
import urllib
import urllib2
import cookielib
import datetime
from bs4 import BeautifulSoup
assignment = []
classes = []
cj = cookielib.CookieJar()
browser = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
browser.addheaders = [('User-Agent', 'Mozilla/5.0')]
def open(url, postdata=None):
if postdata is not None:
postdata = urllib.urlencode(postdata)
return browser.open(url, postdata).read()
USER = 'USERNAME' # these aren't my real credentials
PASS = 'PASSWORD'
URL = 'my school homework website'
now = datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
open(URL)
POST = {'username': USER,
'password': PASS,
'date': now}
loggedIn = open(URL, POST)
soup = BeautifulSoup(loggedIn, "html.parser")
for span in soup.find_all('span', {'class':'title'}):
assignment.append(span.get_text())
for div in soup.find_all('div', {'class':'sub', 'style':'white-space: normal;'}):
classes.append(div.get_text())
for i in range(0, len(assignment)):
print 'for ', classes[i], 'your homework is ', assignment[i]
这是抛出错误的Lambda代码：
import urllib
import urllib2
import cookielib
import datetime
from bs4 import BeautifulSoup
assignment = []
classes = []
final_assignments = []
cj = cookielib.CookieJar()
browser = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
browser.addheaders = [('User-Agent', 'Mozilla/5.0')]
def open(url, postdata=None):
if postdata is not None:
postdata = urllib.urlencode(postdata)
return browser.open(url, postdata).read()
USER = 'USERNAME' # Not my actual Credentials
PASS = 'PASSWORD'
URL = 'my school homework website'
now = datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
def build_speechlet_response(title, output, reprompt_text, should_end_session):
return {
'outputSpeech': {
'type': 'PlainText',
'text': output
},
'card': {
'type': 'Simple',
'title': title,
'content': output
},
'reprompt': {
'outputSpeech': {
'type': 'PlainText',
'text': reprompt_text
}
},
'shouldEndSession': should_end_session
}
def build_response(session_attributes, speechlet_response):
return {
'version': '1.0',
'sessionAttributes': session_attributes,
'response': speechlet_response
}
# --------------- Functions that control the skill's behavior ------------------
def handle_session_end_request():
card_title = "Session Ended"
speech_output = "Thank you for using Homework Retriever!"
# Setting this to true ends the session and exits the skill.
should_end_session = True
return build_response({}, build_speechlet_response(
card_title, speech_output, None, should_end_session))
# --------------- Events ------------------
def on_session_started(session_started_request, session):
""" Called when the session starts """
print("on_session_started requestId=" + session_started_request['requestId']
+ ", sessionId=" + session['sessionId'])
def on_launch(launch_request, session):
""" Called when the user launches the skill without specifying what they
want
"""
print("on_launch requestId=" + launch_request['requestId'] +
", sessionId=" + session['sessionId'])
# Dispatch to your skill's launch
return scraper(session)
def on_session_ended(session_ended_request, session):
""" Called when the user ends the session.
Is not called when the skill returns should_end_session=true
"""
print("on_session_ended requestId=" + session_ended_request['requestId'] +
", sessionId=" + session['sessionId'])
# add cleanup logic here
# --------------- Main handler ------------------
def scraper(session):
sessionAttributes = session.get('attributes', {})
open(URL)
POST = {'username': USER,
'password': PASS,
'date': now}
loggedIn = open(URL, POST)
soup = BeautifulSoup(loggedIn, "html.parser")
for span in soup.find_all('span', {'class':'title'}):
assignment.append(span.get_text())
for div in soup.find_all('div', {'class':'sub', 'style':'white-space: normal;'}):
classes.append(div.get_text())
for i in range(0, len(assignment)):
assignment_not_finished = "for " + str(classes[i]) + "your homework is " + str(assignment[i])
final_assignments.append(str(assignment_not_finished))
return build_response(sessionAttributes, build_speechlet_response(
'Your Homework', str(final_assignments), 'null', True))
def lambda_handler(event, context):
""" Route the incoming request based on type (LaunchRequest, IntentRequest,
etc.) The JSON body of the request is provided in the event parameter.
"""
print("event.session.application.applicationId=" +
event['session']['application']['applicationId'])
"""
Uncomment this if statement and populate with your skill's application ID to
prevent someone else from configuring a skill that sends requests to this
function.
"""
# if (event['session']['application']['applicationId'] !=
# "amzn1.echo-sdk-ams.app.[unique-value-here]"):
# raise ValueError("Invalid Application ID")
if event['session']['new']:
on_session_started({'requestId': event['request']['requestId']},
event['session'])
if event['request']['type'] == "LaunchRequest":
return on_launch(event['request'], event['session'])
elif event['request']['type'] == "IntentRequest":
return on_intent(event['request'], event['session'])
elif event['request']['type'] == "SessionEndedRequest":
return on_session_ended(event['request'], event['session'])
搬家后：
cj = cookielib.CookieJar() browser = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) browser.addheaders = [('User-Agent', 'Mozilla/5.0')] def open(url, postdata=None): if postdata is not None: postdata = urllib.urlencode(postdata) return browser.open(url, postdata).read() USER = 'USERNAME' # Not my actual Credentials PASS = 'PASSWORD' URL = 'my school homework website' now = datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
进入刮刀功能它正在工作