Python-数据不完整(Web抓取)
这是我的代码:Python-数据不完整(Web抓取),python,web-scraping,beautifulsoup,urllib2,Python,Web Scraping,Beautifulsoup,Urllib2,这是我的代码: from bs4 import BeautifulSoup import urllib2 import re import sys main_url = "http://sukhansara.com/سخن-سرا-پر-خوش-آمدید/newposts/parveenshakir/psghazals/" test_url = urllib2.urlopen(main_url) readHtml = test_url.read() test_url.close()
from bs4 import BeautifulSoup
import urllib2
import re
import sys
main_url = "http://sukhansara.com/سخن-سرا-پر-خوش-آمدید/newposts/parveenshakir/psghazals/"
test_url = urllib2.urlopen(main_url)
readHtml = test_url.read()
test_url.close()
soup = BeautifulSoup(readHtml, "html.parser")
url = soup.find('div',attrs={"class":"entry-content"}).findAll('div', attrs={"class":None})
count = 1
fobj = open('D:\Scrapping\parveen_again2.xml', 'w')
for getting in url:
url = getting.find('a')
if url.has_attr('href'):
urls = url['href']
test_url = urllib2.urlopen(urls, timeout=36)
readHtml = test_url.read()
test_url.close()
soup1 = BeautifulSoup(readHtml, "html.parser")
title = soup1.find('title')
title = title.get_text('+')
title = title.split("|")
author = soup1.find('div',attrs={"class":"entry-meta"}).find('span',attrs={"class":"categories-links"})
author = author.findAll('a')
fobj.write("<add><doc>\n")
fobj.write("<field name=\"id\">sukhansara.com_pg1Author"+author[0].string.encode('utf8')+"Count"+str(count)+"</field>\n")
fobj.write("<field name=\"title\">"+title[0].encode('utf8')+"</field>\n")
fobj.write("<field name=\"content\">")
count += 1
poetry = soup1.find('div',attrs={"class":"entry-content"}).findAll('div')
x=1
check = True
while check:
if poetry[x+1].string.encode('utf8') != author[0].string.encode('utf8'):
fobj.write(poetry[x].string.encode('utf8')+"|")
x+=1
else:
check = False
fobj.write(poetry[x].string.encode('utf8'))
fobj.write("</field>\n")
fobj.write("<field name=\"group\">ur_poetry</field>\n")
fobj.write("<field name=\"author\">"+author[0].string.encode('utf8')+"</field>\n")
fobj.write("<field name=\"url\">"+urls+"</field>\n")
fobj.write("<add><doc>\n\n")
fobj.close()
print "Done printing"
从bs4导入美化组
导入urllib2
进口稀土
导入系统
主url=”http://sukhansara.com/س-س-س-س-ش-ش-ٓ-ی/newposts/parveenshakir/psghazals/”
test_url=urllib2.urlopen(主url)
readHtml=test_url.read()
test_url.close()
soup=BeautifulSoup(readHtml,“html.parser”)
url=soup.find('div',attrs={“class”:“entry content”}).findAll('div',attrs={“class”:None})
计数=1
fobj=open('D:\scrasting\parveen\u again2.xml','w')
要获取url,请执行以下操作:
url=get.find('a')
如果url.has_attr('href'):
url=url['href']
test_url=urllib2.urlopen(url,超时=36)
readHtml=test_url.read()
test_url.close()
soup1=BeautifulSoup(readHtml,“html.parser”)
title=soup1.find('title')
title=title.get_文本(“+”)
title=title.split(“|”)
author=soup1.find('div',attrs={“class”:“entry meta”}.find('span',attrs={“class”:“categories links”})
author=author.findAll('a'))
fobj.write(“\n”)
write(“sukhansara.com_pg1Author”+作者[0].string.encode('utf8')+“Count”+str(Count)+“\n”)
fobj.write(“+title[0]。编码('utf8')+“\n”)
fobj.写(“”)
计数+=1
poetry=soup1.find('div',attrs={“class”:“entry content”}.findAll('div'))
x=1
检查=正确
检查时:
如果诗[x+1].string.encode('utf8')!=作者[0]。字符串。编码('utf8'):
fobj.write(诗歌[x].string.encode('utf8')+“|”)
x+=1
其他:
检查=错误
write(poetry[x].string.encode('utf8'))
fobj.write(“\n”)
写作(“你的诗歌”)
fobj.write(“+author[0].string.encode('utf8')+“\n”)
fobj.write(“+URL+”\n”)
fobj.write(“\n\n”)
fobj.close()
打印“完成打印”
有时我从24个网址上收到24首诗,有时81首。但是几乎有100个URL?每当我达到81岁时,就会出现这种错误
AttributeError:“非类型”对象没有属性“encode”
或者有时设置超时错误。我做错了什么?切换到并维护一个打开的会话应该可以让它工作:
import requests
with requests.Session() as session:
main_url = "http://sukhansara.com/سخن-سرا-پر-خوش-آمدید/newposts/parveenshakir/psghazals/"
readHtml = session.get(main_url).content
soup = BeautifulSoup(readHtml, "html.parser")
# ...