Zip函數不顯示抓取數據的完整列表

Question

我已經寫了一個履帶式工具來從網站中提取價格，名稱和評論。但是當我把它們聚攏在一起時，只有9個結果在30箇中被顯示出來。不知道問題在哪裏。此外，我需要添加下一頁鏈接，在那裏我不喜歡這樣做。

from selenium import webdriver 
from selenium.webdriver.common.by import By 
from selenium.webdriver.common.keys import Keys 
from selenium.webdriver.support.ui import Select 
from selenium.common.exceptions import NoSuchElementException 
import unittest, time, re 
import time 
from scrapy.item import Item, Field 
from selenium import webdriver 
from scrapy.spider import BaseSpider 
from scrapy.contrib.spiders import CrawlSpider, Rule 
from bs4 import BeautifulSoup 
import urllib2 
import sys; 
reload(sys); 
sys.setdefaultencoding("utf8") 


class Agoda(CrawlSpider): 
name = 'agoda' 
allowed_domains = ["agoda.com"] 
start_urls = ["http://www.agoda.com"] 
driver = webdriver.Firefox() 
driver.get("http://www.agoda.com") 
driver.find_element_by_id("ctl00_ctl00_MainContent_area_promo_HomeSearchBox1_TextSearch1_searchText").clear() 
driver.find_element_by_id("ctl00_ctl00_MainContent_area_promo_HomeSearchBox1_TextSearch1_searchText").send_keys("Mumbai") 
driver.find_element_by_xpath("//select[contains(@id,'ddlCheckInDay')]") 
driver.find_element_by_xpath("//option[contains(.,'Mon 09')]").click() 
driver.find_element_by_id("ctl00_ctl00_MainContent_area_promo_HomeSearchBox1_SearchButton").click() 
driver.find_element_by_id("ctl00_ContentMain_rptAB1936_ctl01_rptSearchResultAB1936_ctl01_lnkResult1936" or "ctl00_ContentMain_rptSearchResult_ctl01_lnkResult" or "ctl00_ContentMain_rptSearchResult_ctl01_lnkResult").click() 
#driver.find_element_by_id("ctl00_ContentMain_rptSearchResult_ctl01_lnkResult").click() 
time.sleep(40); 
#print driver.page_source 
TotalResults = driver.find_element_by_xpath("//span[@class='blue ssr_search_text']") 
print TotalResults.text 

html_source = driver.page_source 
soup = BeautifulSoup(html_source) 


names = soup("a", {"class":"hot_name"}) 



prices = soup("span", {"class":"fontxlargeb purple"}) 

reviews = soup("a", {"class":"fontlargeb"}) 

hotel_names = [name[1].get_text() for name in enumerate(names)] #or [name[1].get_text() for name in enumerate(names)] 
prices = [price[1].get_text() for price in enumerate(prices)] 
reviews = [review[1].get_text() for review in enumerate(reviews)] #[price[1].get_text() for price in enumerate(prices)] 

name_price_list = zip(hotel_names, prices, reviews) 

for name, price, review in name_price_list: 
    print name, price, review 

Answer 1

您可以使用izip_longest從itertools

作出這樣的聚合來自各個iterables的元素的迭代器。 如果迭代的長度不均勻，缺少的值將填充 並填充值。迭代繼續進行，直到最長可迭代是 用盡

例如：

>>> import itertools 
>>> l2 = ['a','b','c'] 
>>> l1 = [1, 2] 
>>> list(itertools.izip_longest(l1, l2)) 
[(1, 'a'), (2, 'b'), (None, 'c')]