鍍金池/ 問答/Python/ 爬蟲複寫問題

爬蟲複寫問題

各位大大,我嘗試做一個比價的程式,但是我嘗試讓使用者可以重複輸入想要的書名,搜尋完後可以存在booklist裡,但是booklist都會複寫新的值,舊值都不見了,有沒有辦法可以讓booklist一直增加新的數(shù)值,最後再存入?

以下是我的代碼:

`from bs4 import BeautifulSoup
import time
import requests
import csv
URL="https://search.books.com.tw/search/query/key/{0}/cat/all"
import codecs
def generate_search(url,keyword):

url=url.format(keyword)
return url

def generate_resource(url):

headers={"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64)" "AppleWebKit/537.36 (KHTML, like Gecko)" "Chrome/68.0.3440.106" "Safari/537.36"}
return requests.get(url,headers=headers)

def parse_html(r):

if r.status_code==requests.codes.ok:
    r.encoding='utf8'
    soup=BeautifulSoup(r.text,"lxml")
else:
    print("HTTP 請求錯誤..."+url)
    soup=None
return soup

def get_ISBN(url):

soup=parse_html(generate_resource(url))
if soup!=None:
        gogo=soup.find(itemprop="productID")["content"][5:]
        if(gogo!=-1):
            return gogo
        else:
            gogo=None
            return gogo
else:
    return None

def get_prices(isbn):

price1,price2=None,None
url1="http://www.eslite.com/Search_BW.aspx?query="+isbn
soup=parse_html(generate_resource(url1))
if soup!=None:
    price1=soup.find_all("span",class_=["price_sale","特價"])[2].text
else:
    price1=None
url2="https://www.kingstone.com.tw/search/result.asp?c_name={0}&se_type=4"
soup=parse_html(generate_resource(url2.format(isbn)))
if soup !=None:
    price2=soup.find("span",class_="sale_price").text
if (isbn==None):
    price1=None
    price2=None
    return price1,price2
else:
    return price1,price2

def web_scraping_bot(url):

booklist=[]
print("網(wǎng)路抓取資料")
soup=parse_html(generate_resource(url))
if soup!=None:
    tag_item=soup.find_all(class_="item")
    for item in tag_item:
        book=[]
        book.append(item.find("img")["alt"])
        isbn=get_ISBN("https:"+item.find("a")["href"])
        book.append(isbn)
        price=item.find(class_="price").find_all("b")
        book.append(price[1].string+"元")
        price1,price2=get_prices(isbn)
        book.append(price1)
        book.append(price2)
        booklist.append(book)
        print("Wait for 2 secs...")
        time.sleep(2)
return booklist

data=[["名字","ISBN","博客來","誠品","金石堂"]]
def save_to_csv(booklist,file):

with codecs.open(file,'w+','utf_8_sig') as fp:
    writer =csv.writer(fp)
    writer.writerows(data)
    for book in booklist:
        writer.writerow(book)

while True:

name=input("請輸入書名:")
url=generate_search(URL,name)
print(url)
booklist=web_scraping_bot(url)
for item in booklist:
    print(item)
save_to_csv(booklist,"booklist6.csv")
print("要再輸入書名嗎?y/n")
y_b=input()
if(y_b=="y"):
    continue
else:
    break`

回答
編輯回答
厭遇

booklist=[]
把這個放到外面

2018年1月16日 10:44