Estou tentando escrever um cron job para executar periodicamente um script python que escrevi, o que adicionará alguns dados a um banco de dados que estou construindo. O script funciona e funciona quando eu executo python /Users/me/Desktop/pythonScript/script.py do terminal, mas a tarefa cron não está funcionando. Eu corri, chmod a+x /Users/me/Desktop/pythonScript/script.py para tornar o script executável. O script python também começa com #!/usr/bin/python .
Eu adicionei o resultado de $PATH como a variável PATH no meu crontab , como recomendado aqui , além de adicionar variáveis SHELL e HOME .
crontab -l atualmente retorna isso:
PATH="/Library/Frameworks/Python.framework/Versions/3.6/bin:/Users/cole/anaconda/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:/opt/X11/bin:/Library/TeX/texbin"
SHELL="/bin/bash"
HOME = "/Users/me/Desktop/pythonScript/"
* * * * * python script.py
* * * * * env > /tmp/cronenv
O primeiro trabalho é suposto para executar meu script script.py , enquanto o segundo imprime o ambiente cron para o arquivo tmp/cronenv . Este arquivo é assim:
SHELL=/bin/bash
USER=me
PATH=/Library/Frameworks/Python.framework/Versions/3.6/bin:/Users/cole/anaconda/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/Library/Frameworks/Python.framework/Versions/3.5/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:/opt/X11/bin:/Library/TeX/texbin
PWD=/Users/cole
SHLVL=1
HOME=/Users/cole
LOGNAME=cole
_=/usr/bin/env
No entanto, meu banco de dados não está atualizando e quando eu pesquiso cron no meu arquivo system.log, eu encontro as seguintes mensagens de erro:
Nov 5 20:24:00 Coles-MacBook-Air-2 cron[3301]: no path for address 0x11a77b000
Nov 5 20:24:00 Coles-MacBook-Air-2 cron[3302]: no path for address 0x11a77b000
Nov 5 20:25:00 Coles-MacBook-Air-2 cron[3314]: no path for address 0x11a77b000
Nov 5 20:25:00 Coles-MacBook-Air-2 cron[3315]: no path for address 0x11a77b000
Note que há dois para cada minuto, um para cada cronjob , embora o segundo pareça estar funcionando enquanto o primeiro não está. Alguma sugestão?
Como pode ser relevante, este é o script:
script.py
#!/usr/bin/python
# -*- coding: utf-8 -*-
import requests
import re
from nltk import word_tokenize
import time
import pickle
saveDir = '/Users/me/Desktop/pythonScript/dbfolder' #the folder where I want to save files
workingDir = '/Users/me/Desktop/pythonScript/' #location of the script
#this function turns integer values into their url location at a gutenberg mirror
home = 'http://mirror.csclub.uwaterloo.ca/gutenberg/'
fileType = '.txt'
def urlMaker(x):
url = home
if int(x) > 10:
for j in [i for i in range(len(x)-1)]:
url += x[j]+'/'
url += x+'/'+x+fileType
else:
url = home+'0/'+x+'/'+x+fileType
return(url)
#this function takes a url and returns the .txt files at each url, as w as a list of cleaned paragraphs over 100 words in length.
def process(url):
try:
r = requests.get(url)
except ConnectionError:
time.sleep(300)
try:
r = requests.get(url)
except ConnectionError:
time.sleep(600)
try:
r = requests.get(url)
except ConnectionError:
return(ConnectionError)
toprint = r.text
text = r.text.lower()
k = re.search('\Send\Sthe small print!',text)
l = re.search('the project gutenberg etext of the declaration of independence',text)
m = re.search('start of (.*) project gutenberg (.*)*', text)
n = re.search('end of (.*) project gutenberg (.*)*', text)
o = re.search('http://gutenberg.net.au/licence.html', text)
p = re.search('this site is full of free ebooks', text)
x = 0
lst = []
if m and n:
start,end = re.escape(m.group(0)), re.escape(n.group(0))
text = re.search('{}(.*){}'.format(start, end), text, re.S).group(1)
elif o and p:
start,end = re.escape(o.group(0)), re.escape(p.group(0))
text = re.search('{}(.*){}'.format(start, end), text, re.S).group(1)
elif l and n:
start,end = re.escape(l.group(0)), re.escape(n.group(0))
text = re.search('{}(.*){}'.format(start, end), text, re.S).group(1)
elif k and n:
start,end = re.escape(k.group(0)), re.escape(n.group(0))
text = re.search('{}(.*){}'.format(start, end), text, re.S).group(1)
else:
text = text
if text.split('\n\n') != [text]:
for i in text.split('\n\n'):
if i != ''\
and 'gutenberg' not in i\
and 'ebook' not in i\
and 'etext' not in i\
and len(word_tokenize(i)) > 100:
lst += [i.replace('\n',' ')]
x = 1
if text.split('\r\n\r\n') != [text] and x == 0:
for i in text.split('\r\n\r\n'):
if i != ''\
and 'gutenberg' not in i\
and 'ebook' not in i\
and 'etext' not in i\
and len(word_tokenize(i)) > 100:
lst += [i.replace('\r\n',' ')]
return((lst,toprint))
####makes an index dictionary of the titles to the title number
indexUrl = 'http://mirror.csclub.uwaterloo.ca/gutenberg/GUTINDEX.ALL'
r = requests.get(indexUrl)
index = r.text.lower()
#plits index file by beginning and end
start = re.escape(re.search('~ ~ ~ ~ posting dates for the below ebooks: 1 oct 2017 to 31 oct 2017 ~ ~ ~ ~'\
,index).group(0))
end = re.escape(re.search('<==end of gutindex.all==>',index).group(0))
index = re.search('{}(.*){}'.format(start, end), index, re.S).group(1)
#splits file by pc line breaks
lbPC = re.split('\r\n\r\n',index)
#cleans subtitles from line using PC notation
cleanSubsPC = []
for i in lbPC:
cleanSubsPC += [i.split('\r\n')[0]]
#splits lines which use MAC notation
lbMAC = []
for i in cleanSubsPC:
if re.split('\n\n',i) == [i]:
lbMAC += [i]
else:
lbMAC += [x for x in re.split('\n\n',i)]
#cleans subtitles etc. which use MAC linebreaks
cleanSubsMAC = []
for i in lbMAC:
cleanSubsMAC += [i.split('\n')[0]]
#builds list of strings containing titles and numbers, cleaned of weird unicode stuff
textPairs = []
for i in cleanSubsMAC:
if len(i) > 1 and not i =='':
if not i.startswith('~ ~ ~ ~ posting')\
and not i.startswith('title and author'):
try:
int(i[-1])
textPairs += [i.replace('â','')\
.replace('â\xa0',' ').replace('\xa0',' ')]
except ValueError:
pass
#builds dic of key:title pairs
inDic = {}
for i in textPairs:
inDic[int(re.match('.*?([0-9]+)$', i).group(1))] = i.split(' ')[0].replace(',',' ')
#makes dictionary of urls to access
urls = {}
for x in [x for x in range(1,55863)]:
urls[x] = urlMaker(str(x))
#this opens a saved dictionary of the collected data, so the script will begin where it left off previously
try:
with open(workingDir+'gutenburgDic', 'rb') as handle:
data = pickle.load(handle)
except FileNotFoundError:
pass
#actually iterates through urls, saving data, 100 texts at a time. Also saves raw text files for later use
for i in range(len(data)+1,len(data)+101):
data[i],text = (urls[i],process(urls[i])[0]),process(urls[i])[1]
f = open(saveDir+urls[i].replace('/','.'),'w')
f.write(text)
f.close()
#saves updated dictionary of >100 word paragraphs
with open(workingDir+'gutenburgDic', 'wb') as handle:
pickle.dump(data, handle, protocol=pickle.HIGHEST_PROTOCOL)