lxml不使用django,scraperwiki
-
20-12-2019 - |
题
我正在研究一个django应用程序,通过伊利诺伊州的大会网站刮取一些pdf。在我的桌面上部署时,它可以正常工作,直到urllib2超时。当我尝试在我的Bluehost服务器上部署时,代码的lxml部分会引发错误。任何帮助将不胜感激。
import scraperwiki
from bs4 import BeautifulSoup
import urllib2
import lxml.etree
import re
from django.core.management.base import BaseCommand
from legi.models import Votes
class Command(BaseCommand):
def handle(self, *args, **options):
chmbrs =['http://www.ilga.gov/house/', 'http://www.ilga.gov/senate/']
for chmbr in chmbrs:
site = chmbr
url = urllib2.urlopen(site)
content = url.read()
soup = BeautifulSoup(content)
links = []
linkStats = []
x=0
y=0
table = soup.find('table', cellpadding=3)
for a in soup.findAll('a',href=True):
if re.findall('Bills', a['href']):
l = (site + a['href']+'&Primary=True')
links.append(str(l))
x+=1
print x
for link in links:
url = urllib2.urlopen(link)
content = url.read()
soup = BeautifulSoup(content)
table = soup.find('table', cellpadding=3)
for a in table.findAll('a',href=True):
if re.findall('BillStatus', a['href']):
linkStats.append(str('http://ilga.gov'+a['href']))
for linkStat in linkStats:
url = urllib2.urlopen(linkStat)
content = url.read()
soup = BeautifulSoup(content)
for a in soup.findAll('a',href=True):
if re.findall('votehistory', a['href']):
vl = 'http://ilga.gov/legislation/'+a['href']
url = urllib2.urlopen(vl)
content = url.read()
soup = BeautifulSoup(content)
for b in soup.findAll('a',href=True):
if re.findall('votehistory', b['href']):
llink = 'http://ilga.gov'+b['href']
try:
u = urllib2.urlopen(llink)
x = scraperwiki.pdftoxml(u.read())
root = lxml.etree.fromstring(x)
pages = list(root)
chamber = str()
for page in pages:
print "working_1"
for el in page:
print "working_2"
if el.tag == 'text':
if int(el.attrib['top']) == 168:
chamber = el.text
if re.findall("Senate Vote", chamber):
if int(el.attrib['top']) >= 203 and int(el.attrib['top']) < 231:
title = el.text
if (re.findall('House', title)):
title = (re.findall('[0-9]+', title))
title = "HB"+title[0]
elif (re.findall('Senate', title)):
title = (re.findall('[0-9]+', title))
title = "SB"+title[0]
if int(el.attrib['top']) >350 and int(el.attrib['top']) <650:
r = el.text
names = re.findall(r'[A-z-\u00F1]{3,}',r)
vs = re.findall(r'[A-Z]{1,2}\s',r)
for name in names:
legi = name
for vote in vs:
v = vote
if Votes.objects.filter(legislation=title).exists() == False:
c = Votes(legislation=title, legislator=legi, vote=v)
c.save()
print 'saved'
else:
print 'not saved'
elif int(el.attrib['top']) == 189:
chamber = el.text
if re.findall("HOUSE ROLL CALL", chamber):
if int(el.attrib['top']) > 200 and int(el.attrib['top']) <215:
title = el.text
if (re.findall('HOUSE', title)):
title = (re.findall('[0-9]+', title))
title = "HB"+title[0]
elif (re.findall('SENATE', title)):
title = (re.findall('[0-9]+', title))
title = "SB"+title[0]
if int(el.attrib['top']) >385 and int(el.attrib['top']) <1000:
r = el.text
names = re.findall(r'[A-z-\u00F1]{3,}',r)
votes = re.findall(r'[A-Z]{1,2}\s',r)
for name in names:
legi = name
for vote in votes:
v = vote
if Votes.objects.filter(legislation=title).exists() == False:
c = Votes(legislation=title, legislator=legi, vote=v)
c.save()
print 'saved'
else:
print 'not saved'
except:
pass
编辑1 这是错误跟踪
Traceback (most recent call last):
File "manage.py", line 10, in <module>
execute_from_command_line(sys.argv)
File "/home7/maythirt/python27/lib/python2.7/site-packages/django/core/management/__init__.py", line 399, in execute_from_command_line
utility.execute()
File "/home7/maythirt/python27/lib/python2.7/site-packages/django/core/management/__init__.py", line 392, in execute
self.fetch_command(subcommand).run_from_argv(self.argv)
File "/home7/maythirt/python27/lib/python2.7/site-packages/django/core/management/base.py", line 242, in run_from_argv
self.execute(*args, **options.__dict__)
File "/home7/maythirt/python27/lib/python2.7/site-packages/django/core/management/base.py", line 285, in execute
output = self.handle(*args, **options)
File "/home7/maythirt/GAB/legi/management/commands/vote.py", line 51, in handle
root = lxml.etree.fromstring(x)
File "lxml.etree.pyx", line 3032, in lxml.etree.fromstring (src/lxml/lxml.etree.c:68121)
File "parser.pxi", line 1786, in lxml.etree._parseMemoryDocument (src/lxml/lxml.etree.c:102470)
File "parser.pxi", line 1674, in lxml.etree._parseDoc (src/lxml/lxml.etree.c:101299)
File "parser.pxi", line 1074, in lxml.etree._BaseParser._parseDoc (src/lxml/lxml.etree.c:96481)
File "parser.pxi", line 582, in lxml.etree._ParserContext._handleParseResultDoc (src/lxml/lxml.etree.c:91290)
File "parser.pxi", line 683, in lxml.etree._handleParseResult (src/lxml/lxml.etree.c:92476)
File "parser.pxi", line 633, in lxml.etree._raiseParseError (src/lxml/lxml.etree.c:91939)
lxml.etree.XMLSyntaxError: None
解决方案
正如乔纳森所提到的,它可能是 scraperwiki.pdftoxml()
这是个问题。您可以显示或记录 x
来确认。
具体来说, pdftoxml()
运行外部程序 pdftohtml
并使用临时文件来存储PDF和XML。
我还要检查的是:
- 是
pdftohtml
正确设置 在您的服务器上? - 如果是这样,如果您直接在服务器上的shell中使用代码失败的PDF运行它,则转换为XML是否有效?它正在执行的命令是
pdftohtml -xml -nodrm -zoom 1.5 -enc UTF-8 -noframes "input.pdf" "output.xml"
如果直接运行命令时出现问题,那么问题就在于此。用的方式 pdftohtml
在 scraperwiki
代码,没有简单的方法可以判断命令是否失败。
其他提示
他们会去的方式,添加一个尝试这样您就可以单独检查XML文件。
可能是scraperwiki.pdftoxml出于某种原因的非法XML文件。使用另一个PDFTOXML工具时,我已经发生在我身上。
并请将代码重构为更多功能,它将更容易阅读和维护:)。
另一种方式将首先下载所有PDF,然后解析它们。这样,您可以在某种原因失败时避免使用几次网站。
不隶属于 StackOverflow