Question

我和朋友使用BeautifulSoup创建了以下脚本来获取作业页面的HTML，然后将作业附加到数组，然后是文件，然后以人类可读的格式将作业发送给我们自己。该脚本适用于Ubuntu，但在使用Raspbian的Raspberry Pi上，它不起作用。

我从终端运行时看到的唯一消息是：＆＃39;文件结尾＆＃39;并且＆＃39;开始写...＆＃39;这是代码中的行。从Pi运行时没有错误消息，但没有任何内容被附加到数组，也没有发送电子邮件。

有人可以看看吗？感谢。

import urllib2, email, smtplib, os.path
import cPickle as pickle
from bs4 import BeautifulSoup

class Job:
    """docstring for Job"""
    def __init__(self, title, date, url):
        self.title = title
        self.date = date
        self.url = "http://www.forensicfocus.com/"+url
    def describJob(self):
        return (self.title +" "+ self.date +" "+ self.url)

def createJobsArray():
    soup = BeautifulSoup(urllib2.urlopen('http://www.forensicfocus.com/jobs').read())
    bigFatString = soup.find_all('a')
    #print(bigFatString) #this gets webpage as html. No issues here
    findAll = soup.find_all("tr", class_="topic")
    jobsArray = []
    for section in findAll:
        title = section.find("a", class_="topictitle").get_text()
        titleEncoded = title.encode('ascii','ignore')
        row = section.find_all("td")
        date = row[3].find("div").get_text()
        url = section.find_all("a")[3].get("href")
        job = Job(titleEncoded, date, url)
        print "printing job"
        print job
        print "printing job"
        jobsArray.append(job)
    return jobsArray


def sendEmail(job):
    senderEmail = "sender@example.com"
    recipients = ["destination@example.com"]
    s = smtplib.SMTP("smtp.gmail.com",587)
    s.ehlo()
    s.starttls() 
    s.ehlo()
    s.login(senderEmail, 'pass_goes_here')
    for job in jobsFilteredByLocation:
        msg = email.message_from_string(job.describJob())
        msg['Subject'] = "New Job Found: " + job.title
        s.sendmail(senderEmail, recipients, msg.as_string())
        print "Sending email..."
    s.quit()

def saveJobsToDisk(jobs):
    with open('hadooken', 'wb') as output:
        print "Start write..."
        for job in jobs:
            print job.title
            pickle.dump(job, output)
        output.close()

def getJobsFromDisk():
    oldJobsArray = []
    with open('hadooken', 'rb') as input:
        while True:
            try:
                job = pickle.load(input)
                print job.title, "was successfully read from file"
                oldJobsArray.append(job)
            except EOFError:
                print "end of file"
                break   
        return oldJobsArray
        input.close()

# SCRIPT STARTS HERE        
with open('hadooken', 'ab') as input:
    input.close()

locationsArray = ["London"]
jobsArray = createJobsArray()

oldJobsArray = getJobsFromDisk()

jobsFilteredByLocation = []

for job in jobsArray:
    for location in locationsArray:

        found = job.title.find(location)

        if found > 0:
            if len(oldJobsArray) > 0:
                if any(oldJob.title == job.title for oldJob in oldJobsArray):
                    print "Job previously found and sent..."
                else:
                    print "adding ", job.title, "to array because it isnt in the old array"
                    jobsFilteredByLocation.append(job)
            else:
                print "adding ", job.title, "to array"
                jobsFilteredByLocation.append(job)

sendEmail(jobsFilteredByLocation)

mergedArray = oldJobsArray + jobsFilteredByLocation

for job in mergedArray:
    print "Job title: ", job.title
saveJobsToDisk(mergedArray)

为什么这个python脚本适用于Ubuntu而不是Raspbian？

0 个答案: