我的以下代碼有問題。import urllib2import csvfrom bs4 import BeautifulSoupsoup = BeautifulSoup(urllib2.urlopen('http://www.ny.com/clubs/nightclubs/index.html').read())clubs = []trains = ["A","C","E","1","2","3","4","5","6","7","N","Q","R","L","B","D","F"]for club in soup.find_all("dt"): clubD = {} clubD["name"] = club.b.get_text() clubD["address"] = club.i.get_text() text = club.dd.get_text() nIndex = text.find("(") if(text[nIndex+1]=="2"): clubD["number"] = text[nIndex:nIndex+15] sIndex = text.find("Subway") sIndexEnd = text.find(".",sIndex) if(text[sIndexEnd-1] == "W" or text[sIndexEnd -1] == "E"): sIndexEnd2 = text.find(".",sIndexEnd+1) clubD["Subway"] = text[sIndex:sIndexEnd2] else: clubD["Subway"] = text[sIndex:sIndexEnd] try: cool = clubD["number"] except (ValueError,KeyError): clubD["number"] = "N/A" clubs.append(clubD)keys = [u"name", u"address",u"number",u"Subway"]f = open('club.csv', 'wb')dict_writer = csv.DictWriter(f, keys)dict_writer.writerow([unicode(s).encode("utf-8") for s in clubs])我收到錯誤ValueError：dict包含不在字段名稱中的字段。我不明白這怎么可能。任何幫助將是巨大的。我正在嘗試將字典轉換為Excel文件。
1 回答
小唯快跑啊
TA貢獻1863條經驗 獲得超2個贊
clubs是詞典列表，而每個詞典都有四個字段：名稱，地址，編號和Subway。您將需要對每個字段進行編碼：
# Instead of:
#dict_writer.writerow([unicode(s).encode("utf-8") for s in clubs])
# Do this:
for c in clubs:
# Encode each field: name, address, ...
for k in c.keys():
c[k] = c[k].encode('utf-8').strip()
# Write to file
dict_writer.writerow(c)
更新
我查看了您的數據，其中一些字段以結尾換行\n，因此我更新了代碼以同時編碼和去除空格。
添加回答
舉報
0/150
提交
取消