Question

我正在使用以下代码从Yahoo!中删除数据但是，我对第一个异常语句所做的修改导致代码循环......根本没有任何内容写入CSV文件。目前，我正在通过调试器来处理此错误。我认为错误是在while循环中引起的。

import urllib2
from BeautifulSoup import BeautifulSoup
import csv
import re
import urllib
from urllib2 import HTTPError
# import modules

symbolfile = open("symbols.txt")
symbolslist = symbolfile.read()
newsymbolslist = symbolslist.split("\n")

i = 0

f = csv.writer(open("pe_ratio.csv","wb"))
# short cut to write

f.writerow(["Name","PE","Revenue % Quarterly","ROA% YOY","Operating Cashflow","Debt to Equity"])
#first write row statement

# define name_company as the following
while i<len(newsymbolslist):
    try:
        page = urllib2.urlopen("http://finance.yahoo.com/q/ks?s="+newsymbolslist[i] +"%20Key%20Statistics").read()
    except urllib2.HTTPError:
        continue
        soup = BeautifulSoup(page)
        name_company = soup.findAll("div", {"class" : "title"}) 
        for name in name_company: #add multiple iterations?        
            all_data = soup.findAll('td', "yfnc_tabledata1")
            stock_name = name.find('h2').string #find company's name in name_company with h2 tag
            try:    
                f.writerow([stock_name, all_data[2].getText(),all_data[17].getText(),all_data[13].getText(), all_data[29].getText(),all_data[26].getText()]) #write down PE data
            except (IndexError, HTTPError) as e:
                pass
            i+=1

提前感谢您的帮助。

Answer 1

尝试先将i = i + 1缩进一个，因此它在单独的for循环之外？我还将“继续”之后的代码缩进放在与try相同的行上，除非，否则它只会在except情况下运行（或者因为继续而完全传递）。

while i<len(newsymbolslist):
    try:
        page = urllib2.urlopen("http://finance.yahoo.com/q/ks?s="+newsymbolslist[i] +"%20Key%20Statistics").read()
    except urllib2.HTTPError:
        continue
    soup = BeautifulSoup(page)
    name_company = soup.findAll("div", {"class" : "title"}) 
    for name in name_company: #add multiple iterations?        
        all_data = soup.findAll('td', "yfnc_tabledata1")
        stock_name = name.find('h2').string #find company's name in name_company with h2 tag
        try:    
            f.writerow([stock_name, all_data[2].getText(),all_data[17].getText(),all_data[13].getText(), all_data[29].getText(),all_data[26].getText()]) #write down PE data
        except (IndexError, HTTPError) as e:
            pass
    i+=1

Answer 2

我认为缩进是错误的。试试这个：

from BeautifulSoup import BeautifulSoup
import csv
import re
import urllib
from urllib2 import HTTPError
# import modules

symbolfile = open("symbols.txt")
symbolslist = symbolfile.read()
newsymbolslist = symbolslist.split("\n")

i = 0

f = csv.writer(open("pe_ratio.csv","wb"))
# short cut to write

f.writerow(["Name","PE","Revenue % Quarterly","ROA% YOY","Operating Cashflow","Debt to Equity"])
#first write row statement

# define name_company as the following
while i<len(newsymbolslist):
    try:
        page = urllib2.urlopen("http://finance.yahoo.com/q/ks?s="+newsymbolslist[i] +"%20Key%20Statistics").read()
    except urllib2.HTTPError:
        continue
    soup = BeautifulSoup(page)
    name_company = soup.findAll("div", {"class" : "title"}) 
    for name in name_company: #add multiple iterations?        
        all_data = soup.findAll('td', "yfnc_tabledata1")
        stock_name = name.find('h2').string #find company's name in name_company with h2 tag
        try:    
            f.writerow([stock_name, all_data[2].getText(),all_data[17].getText(),all_data[13].getText(), all_data[29].getText(),all_data[26].getText()]) #write down PE data
        except (IndexError, HTTPError) as e:
            pass
    i+=1

Python嵌套循环格式

2 个答案: