我有一个从网站上提取的脚本,它似乎不想将数据写入csv。 我假设我的for循环有问题,以及它是如何写出来的。有人会看看我,看看你会如何改变它?我在这里错过了什么。
感谢您的帮助。
下面是python脚本 - 再次,我认为问题在于底部的for循环。
from urllib.request import urlopen as uReq
from bs4 import BeautifulSoup as soup
# setting my_url to the wesite
urls = ['https://www.extraspace.com/Storage/Facilities/US/North_Carolina/Charlotte/1000000398/Facility.aspx'
, 'https://www.extraspace.com/Storage/Facilities/US/North_Carolina/Charlotte/1000000404/Facility.aspx']
filename = "extraspace.csv"
open(filename, 'w').close()
f = open(filename, "a")
num = 0
headers = "unit_size, size_dim1, unit_type, online_price, reg_price, street_address, store_city, store_postalcode\n"
f.write(headers)
for my_url in urls:
# Opening up connection, grabbing the page
uClient = uReq(my_url)
# naming uClient to page_html
page_html = uClient.read()
# closing uClient
uClient.close()
# this does my html parsing
page_soup = soup(page_html, "html.parser")
# setting container to capture where the actual info is using inspect element
#grabs each product
containers = page_soup.findAll("div", {"itemprop": "makesOffer"})
#grabs address
store_locator = page_soup.findAll("div", {"itemprop": "address"})
f.write("website " + str(num) + ": \n")
for container in containers:
for store_location in store_locator:
street_address = store_location.findAll("span", {"itemprop": "streetAddress"})
store_city = store_location.findAll("span", {"itemprop": "addressLocality"})
store_postalcode = store_location.findAll("spand", {"itemprop": "postalCode"})
title_container = container.findAll("div", {"class": "size RamaGothicSemiBold"})
size_dim = container.findAll("div", {"itemprop": "description"})
unit_container = container.ul.li
unit_type = container.text
online_price = container.findAll("div", {"itemprop": "price"})
reg_price = container.findAll("div", {"class": "rate strikeout"})
for item in zip(title_container, size_dim, unit_type, online_price, reg_price, street_address, store_city, store_postalcode):
csv = item[0].text + "," + item[1].text + "," + item[2] + "," + item[3].text + "," + item[4].text + "," + item[5].text + "," + item[6].text + "," + item[7].text + "\n"
f.write(csv)
num += 1
这是容器的HTML:
<div itemprop="makesOffer" itemscope="" itemtype="http://schema.org/Offer">
<div itemprop="itemOffered" itemscope="" itemtype="http://schema.org/Product">
<div class="guide">
<div class="size-help-lnk size-guide hidden" data-locker="False" data-square-feet="25">Size Help</div>
<div alt="5x5" class="video-btn-5x5 video-link" onclick="trackSC('UnitListingVideo');"></div>
</div>
<div class="size RamaGothicSemiBold">
<div itemprop="description">5' x 5'</div>
<div>SMALL</div>
</div>
<div class="features">
<ul itemprop="description">
<li><i class="check-icon"></i>Enclosed Storage</li>
<li><i class="check-icon"></i>Indoor</li>
<li><i class="check-icon"></i>1st Floor Access</li>
</ul>
</div>
</div>
<div>
<div class="rate strikeout">
<div><span style="width:100%;"></span>$57</div><span class="StreetRate">IN-STORE</span></div>
<div class="rate">
<div content="35.00" itemprop="price">$35
<meta content="USD" itemprop="priceCurrency" />
</div><span class="WebRate">WEB RATE</span></div>
<div class="promo"><span style="color:#000;">Act fast:<br/>Limited units</span></div>
</div>
<a class="btn btn-orange cta-test is-vehicle" href="https://www.extraspace.com/Storage/ReserveOrHold.aspx?uid=a0GC000000tUNupMAG" id="ctl00_mContent_UnitListPopular_ctrl0_hlReserveLink" onclick="upDown('unitRows|8506|1;05X05|NDN|57|35| | ; | | | | | ; | | | | | ;05X05|CDN|71|48| | ;05X07|CDN|74|50| | ');">RESERVE</a>
<div class="clear"></div>
<link href="http://schema.org/OnlineOnly" itemprop="availability">
</link>
</div>
以下是store_locator的html;
[ < div itemprop = "address"
itemscope = ""
itemtype = "http://schema.org/PostalAddress" >
<
span id = "ctl00_mContent_lbAddress"
itemprop = "streetAddress" > 3304 Eastway Dr < br / > Ste D < /span><br/ >
<
span id = "ctl00_mContent_lbCity"
itemprop = "addressLocality" > Charlotte < /span>, <
span id = "ctl00_mContent_lbState"
itemprop = "addressRegion" > NC < /span> <
span id = "ctl00_mContent_lbPostalCode"
itemprop = "postalCode" > 28205 < /span> <
/div>]