152644841056 有2个价格(已解决)
import random
from http.cookiejar import CookieJar
import requests
from bs4 import BeautifulSoup
import csv
import numpy as np
import re
class EbaySpider(object):
def __init__(self):
self.SESSION = requests.session()
self.SESSION.cookies = CookieJar()
# print(self.SESSION.cookies)
self.HEAD = self.randHeader()
def randHeader(self):
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
def getBeautifulSoup(self, query_rl):
r = self.SESSION.get(url=query_rl, headers=self.HEAD)
# print(self.SESSION.cookies)
soup = BeautifulSoup(r.text, 'html.parser')
return soup
def getRates(self, query_url):
r = self.SESSION.get(url=query_url, headers=self.HEAD)
# print(self.SESSION.cookies)
soup = BeautifulSoup(r.text, 'html.parser')
content = soup.find("span", "rcnt")
itemSize = int(content.string)
print("初次查询:" + str(itemSize) + "项")
iid_one = str(soup.find("div", "lvpic pic img left"))
l = iid_one.find("iid=")
r = iid_one.find("\">")
itm = str(iid_one[l + 5:r])
print("设置美国Code")
getrates_url = "http://www.ebay.com/itm/getrates?item=" + itm + "&quantity=1&country=1&zipCode=&co=0&cb=jQuery1705300436743778978_1501488303970"
r = self.SESSION.get(url=getrates_url, headers=self.HEAD)
soup = BeautifulSoup(r.text, 'html.parser')
def search(self, serchWords):
serchWords = str(serchWords).replace(" ", "%20")
# _ipg=100每页100 ,
query_rl = "https://www.ebay.com/sch/i.html?_from=R40&_sacat=0&_ipg=100&rt=nc&_nkw=" + serchWords + "&_pgn=1&_skc=0"
self.getRates(query_url=query_rl)
soup = self.getBeautifulSoup(query_rl)
content = soup.find("span", "rcnt") # 抓取网页上总共条数
itemSize = int(content.string.replace(",", ""))
pageSize = int(itemSize / 100)
if itemSize % 100 != 0:
pageSize += 1
print("总计" + str(itemSize) + "项,共" + str(pageSize) + "页(每页100条)")
print("第1页....")
result = []
#抓取每一个商品
content = soup.find_all(attrs={'class' : re.compile('^sresult lvresult clearfix li')})
for i in content:
#抓取商品的eBayno
ebayno = i.find_all("div","lvpic pic img left")[0]['iid']
#抓取商品的价格
price_content = i.li.find("span","bold")
cur = price_content.b.string #币种
s = str(price_content)
price_ = re.findall('\d*,?\d*,?\d+\.\d+', s)
price = str(price_[0]).replace(",", "") #价格
result.append([ebayno, cur , price])
for _pgn in range(2, pageSize + 1):
print("第" + str(_pgn) + "页....")
query_rl = "https://www.ebay.com/sch/i.html?_from=R40&_sacat=0&_ipg=100&rt=nc&_nkw=" + serchWords + "&_pgn=" + str(
_pgn) + "&_skc=" + str((_pgn - 1) * 100)
soup = self.getBeautifulSoup(query_rl)
# 抓取每一个商品
content = soup.find_all(attrs={'class': re.compile('^sresult lvresult clearfix li')})
for i in content:
# 抓取商品的eBayno
ebayno = i.find_all("div", "lvpic pic img left")[0]['iid']
# 抓取商品的价格
price_content = i.li.find("span", "bold")
cur = price_content.b.string # 币种
s = str(price_content)
price_ = re.findall('\d*,?\d*,?\d+\.\d+', s)
price = str(price_[0]).replace(",", "") # 价格
result.append([ebayno, cur, price])
return result
if __name__ == '__main__':
ebay = EbaySpider()
result = ebay.search("2006 GMC Sierra 1500 window visor")
out = open("4.csv", "w", newline="")
csv_writer = csv.writer(out)
csv_writer.writerow(["ebayno", "currency", "price"])
for i in range(len(result)):
print(str(i), end="\t")
print(result[i])
csv_writer.writerow([result[i][0], result[i][1], result[i][2]])