from urllib.request import *
import re
import json
import urllib.parse
import urllib.request
from bs4 import BeautifulSoup
import random
def randHeader():
head_connection = ['Keep-Alive', 'close']
head_accept = ['text/html, application/xhtml+xml, */*']
head_accept_language = ['zh-CN,fr-FR;q=0.5', 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']
head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',
'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',
'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',
'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']
header = {
'Connection': head_connection[0],
'Accept': head_accept[0],
'Accept-Language': head_accept_language[1],
'User-Agent': head_user_agent[random.randrange(0, len(head_user_agent))]
}
return header
# url = 'http://www.ebay.com/itm/152586216774'
# req = urllib.request.Request(url= url , headers=randHeader())
# webpage = urllib.request.urlopen(req)
# html = webpage.read()
# soup = BeautifulSoup(html, 'html.parser')
# print(soup)
url = "http://vi.vipr.ebaydesc.com/ws/eBayISAPI.dll?ViewItemDescV4&item=152586216774&t=1500608274000&tid=10&category=33590&seller=odcarparts&vipguid=a5ac9dd515d0aa4826225fdcff3ecb72&excTrk=1&tto=3500&lsite=100&ittenable=false&domain=ebay.com&descgauge=1&cspheader=1"
req = urllib.request.Request(url= url , headers=randHeader())
webpage = urllib.request.urlopen(req)
html = webpage.read()
soup = BeautifulSoup(html, 'html.parser') #解析
content = soup.find_all("div", class_="descriptionbox")[0] #选取desc部分
p = content.find_all("span") #选取段落部分
# print(p[0].strong.string) #p[0]是Description
content = p[1] #p[1]是内容
pp = content.p.prettify() #将内容格式化
pp = BeautifulSoup(pp,"html.parser")#解析
#写文本到txt文件
file_object = open("description.txt", 'w')
file_object.write("Description")
for child in pp.strings:
print(repr(child))
file_object.write(child)
ebay description抓取
最新推荐文章于 2024-04-27 04:48:04 发布