从特定div父母(美丽的汤蟒)获取特定的div标签

时间:2017-09-23 15:59:47

标签: python beautifulsoup

我正在尝试制作网络刮刀,但我遇到了问题

# encoding=utf8

import urllib2
from bs4 import BeautifulSoup
indice = 0
print "     "

quote_page = "https://www.bloomberg.com/quote/INDU:IND"

page = urllib2.urlopen(quote_page)

soup = BeautifulSoup(page, "html.parser")


print "down jones industries"

price_box = soup.find("div", attrs={"class": "price"})
price1 = price_box.text
print price1


divTag = soup.find_all("div", {"class": "cell cell__mobile-basic cell__visible__even"})
print divTag
 in divTag:
    indice = tag.find("div", {"class": "cell__value cell__value_"})

print indice 


if price1 > indice :
    print "UP"
elif price1 == indice :
    print "equal"
elif price1 < indice :
    print "DOWN"




print "     "






quote_page = "link"

page = urllib2.urlopen(quote_page)

soup = BeautifulSoup(page, "html.parser")


print "google"

price_box = soup.find("div", attrs={"class": "price"})
price1 = price_box.text
print price1

divTag = soup.find_all("div", {"class": "cell cell__mobile-basic cell__visible__even"})

for tag in divTag:
    indice = tag.find_all("div", {"class": "cell__value cell__value_"})




if price1 > indice :
    print "UP"
elif price1 == indice :
    print "equal"
elif price1 < indice :
    print "DOWN"



print "     "







quote_page = "link"

page = urllib2.urlopen(quote_page)

soup = BeautifulSoup(page, "html.parser")



print "ibovespa"

price_box = soup.find("div", attrs={"class": "price"})
price1 = price_box.text
print price1
divTag = soup.find_all("div", {"class": "cell cell__mobile-basic cell__visible__even"})

for tag in divTag:
    indice = tag.find_all("div", {"class": "cell__value cell__value_"})




if price1 > indice :
    print "UP"
elif price1 == indice :
    print "equal"
elif price1 < indice :
    print "DOWN"

print "     "










quote_page = "https://www.bloomberg.com/quote/FB:US"

page = urllib2.urlopen(quote_page)

soup = BeautifulSoup(page, "html.parser")


print "facebook"

price_box = soup.find("div", attrs={"class": "price"})
price1 = price_box.text
print price1
divTag = soup.find_all("div", {"class": "cell cell__mobile-basic cell__visible__even"})

for tag in divTag:
    indice = tag.find_all("div", {"class": "cell__value cell__value_"})




if price1 > indice :
    print "UP"
elif price1 == indice :
    print "equal"
elif price1 < indice :
    print "DOWN"

print "     "

` 这是我的代码,我遇到了一个问题:我想从特定的div标签中访问一个特定的div标签,有人可以帮助我!

1 个答案:

答案 0 :(得分:0)

你不需要写刮刀。 Bloomberg有一个记录良好的REST API:

https://www.programmableweb.com/api/bloomberg

从长远来看,这将更容易可靠地使用。