Question

以下脚本成功从单个IP（url_ip）中提取正确的信息。但在尝试构建循环过程后，请求调用会因连接错误而失败。（以下错误） *注意 - 草率代码，所以要注意。

from lxml import html
import requests
import smtplib

# STATIC URL
#TODO PULL A LIST OF IP ADDRESSES AND BUILD THE URL FOR EACH SYSTEM

#IPs = ['192.168.3.152','192.168.3.194']

def crawler(url_ip):
    global eqid, counter, serial
    print "Starting Crawler Service for: " + url_ip
    url = "http://" + url_ip + "/cgi-bin/dynamic/printer/config/reports/deviceinfo.html"
    urleqid = "http://" + url_ip + "/cgi-bin/dynamic/topbar.html"

    response = requests.get(url)
    tree = html.fromstring(response.text)

    counter = tree.xpath('//td[contains(p,"Count")]/following-sibling::td/p/text()')
    serial = tree.xpath('//td[contains(p, "Serial")]/following-sibling::td/p/text()')
    counter = counter[0].split(' ')[3]
    serial = serial[0].split(' ')[3]

    responseeqid = requests.get(urleqid)
    treeequid = html.fromstring(responseeqid.text)
    eqid = treeequid.xpath('//descendant-or-self::node()/child::b[contains(., "Location")]/text()')[1].split(' ')[-1]

    print " -- equipment id found: " + eqid
    print " -- count found: " + counter
    print " -- serial found: " + serial
    print "Stopping Crawler Service for: " + url_ip

    return

def send_mail(eqid,counter,serial):
    GMAIL_USERNAME = "removed"
    GMAIL_PASSWORD = "removed"

    recipient = "removed"
    email_subject = "Test"
    body_of_email = "Equipment ID = " + eqid + "<br>Total Meter Count = " + counter + "<br>Serial Number = " + serial + "<br><br>"

    session = smtplib.SMTP('smtp.gmail.com', 587)
    session.ehlo()
    session.starttls()
    session.login(GMAIL_USERNAME, GMAIL_PASSWORD)

    headers = "\r\n".join(["from: " + GMAIL_USERNAME,
                        "subject: " + email_subject,
                        "to: " + recipient,
                        "mime-version: 1.0",
                        "content-type: text/html"])

    # body_of_email can be plain text or html!                    
    content = headers + "\r\n\r\n" + body_of_email
    session.sendmail(GMAIL_USERNAME, recipient, content)
    return

with open('iplist.txt') as fp:
    for line in fp:
        crawler(line);

#send_mail(eqid,counter,serial);

错误日志：

Starting Crawler Service for: 192.168.3.152

Traceback (most recent call last):
  File "getmeters.py", line 63, in <module>
    crawler(ipstring);
  File "getmeters.py", line 17, in crawler
    response = requests.get(url)
  File "/Library/Python/2.7/site-packages/requests/api.py", line 68, in get
    return request('get', url, **kwargs)
  File "/Library/Python/2.7/site-packages/requests/api.py", line 50, in request
    response = session.request(method=method, url=url, **kwargs)
  File "/Library/Python/2.7/site-packages/requests/sessions.py", line 464, in request
    resp = self.send(prep, **send_kwargs)
  File "/Library/Python/2.7/site-packages/requests/sessions.py", line 576, in send
    r = adapter.send(request, **kwargs)
  File "/Library/Python/2.7/site-packages/requests/adapters.py", line 415, in send
    raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', gaierror(8, 'nodename nor servname provided, or not known'))

我认为这是由于价值＆＃34;线＆＃34;被处理为列表对象而不是字符串，所以我转换为str（行），但也失败了。

Answer 1

我怀疑你在文件行的末尾有行结尾（\ n），你可能需要将它们去掉。否则您的网址会变成

http://192.168.3.152
/cgi-bin/dynamic/printer/config/reports/deviceinfo.html"

而不是预期的

http://192.168.3.152/cgi-bin/dynamic/printer/config/reports/deviceinfo.html"

Python在循环中执行请求函数调用？

1 个答案: