将列表追加到熊猫列

Question

I need to append the list idlist to the column in my table called EventID . The list needs to be appended in order, since I grabbed the ID's in order from the original HTML file.

Right now my output looks like this:

     EventID                   EventDate                                          EventName  AmntTickets              PriceRange
0  103577924  Thu, 10/11/2018  8:20 p.m.  Philadelphia Eagles at New York Giants  MetLif...         6655  $134.50  to  $2,222.50
1  103577924  Thu, 10/11/2018  8:21 p.m.  PARKING PASSES ONLY Philadelphia Eagles at New...          929   $20.39  to  $3,602.50
     EventID                   EventDate                                          EventName  AmntTickets              PriceRange
0  103577925  Thu, 10/11/2018  8:20 p.m.  Philadelphia Eagles at New York Giants  MetLif...         6655  $134.50  to  $2,222.50
1  103577925  Thu, 10/11/2018  8:21 p.m.  PARKING PASSES ONLY Philadelphia Eagles at New...          929   $20.39  to  $3,602.50

I need it to look like this:

     EventID                   EventDate                                          EventName  AmntTickets              PriceRange
0  103577924  Thu, 10/11/2018  8:20 p.m.  Philadelphia Eagles at New York Giants  MetLif...         6655  $134.50  to  $2,222.50
1  103577925  Thu, 10/11/2018  8:21 p.m.  PARKING PASSES ONLY Philadelphia Eagles at New...          929   $20.39  to  $3,602.50

My code:

import pandas as pd
from bs4 import BeautifulSoup
import requests
import lxml.html as lh
import pprint
import re

with open("htmltabletest.html", encoding="utf-8") as f:
    data = f.read()
    soup = BeautifulSoup(data, 'lxml')
    pd.set_option('display.max_rows', 500)
    pd.set_option('display.max_columns', 500)
    pd.set_option('display.width', 1000)
    dfs = pd.read_html(soup.prettify())
    df = dfs[0]
    dfz=df.rename(columns = {'Event date  Time (local)':'EventDate'}).rename(columns = {'Event name  Venue':'EventName'}).rename(columns = {'Tickets  listed':'AmntTickets'}).rename(columns = {'Price  range':'PriceRange'}).rename(columns = {'Unnamed: 0':'EventID'})
    idlist = []
    for se in soup.find_all('span', id=re.compile(r'min')):
        se = (str(se))
        seeme1 = se.replace('<span id="se-','')
        seeme, sep, tail = seeme1.partition('-')
        idlist.append(seeme)
    for p in idlist:
        dfz = dfz.assign(EventID=p)
        print(dfz)

my html file (htmltabletest.html):

<table class="dataTable st-alternateRows" id="eventSearchTable">
<thead>
<tr>
<th id="th-es-rb"><div class="dt-th"> </div></th>
<th id="th-es-ed"><div class="dt-th"><span class="th-divider"> </span>Event date<br/>Time (local)</div></th>
<th id="th-es-en"><div class="dt-th"><span class="th-divider"> </span>Event name<br/>Venue</div></th>
<th id="th-es-ti"><div class="dt-th"><span class="th-divider"> </span>Tickets<br/>listed</div></th>
<th id="th-es-pr"><div class="dt-th es-lastCell"><span class="th-divider"> </span>Price<br/>range</div></th>
</tr>
</thead>
<tbody class="" id="eventSearchTbody"><tr class="even" id="r-se-103577924">
<td class="nowrap"><input class="es-selectedEvent" id="se-103577924-check" name="selectEvent" type="radio"/></td>
<td class="nowrap" id="se-103577924-eventDateTime">Thu, 10/11/2018<br/>8:20 p.m.</td>
<td><div><a class="ellip" href="services/priceanalysis?eventId=103577924&amp;sectionId=0" id="se-103577924-eventName" target="_blank">Philadelphia Eagles at New York Giants</a></div><div id="se-103577924-venue">MetLife Stadium, East Rutherford, NJ</div></td>
<td id="se-103577924-nrTickets">6655</td>
<td class="es-lastCell nowrap" id="se-103577924-priceRange"><span id="se-103577924-minPrice">$134.50</span>  to<br/><span id="se-103577924-maxPrice">$2,222.50</span></td>
</tr><tr class="odd" id="r-se-103577925">
<td class="nowrap"><input class="es-selectedEvent" id="se-103577925-check" name="selectEvent" type="radio"/></td>
<td class="nowrap" id="se-103577925-eventDateTime">Thu, 10/11/2018<br/>8:21 p.m.</td>
<td><div><a class="ellip" href="services/priceanalysis?eventId=103577925&amp;sectionId=0" id="se-103577925-eventName" target="_blank">PARKING PASSES ONLY Philadelphia Eagles at New York Giants</a></div><div id="se-103577925-venue">MetLife Stadium Parking Lots, East Rutherford, NJ</div></td>
<td id="se-103577925-nrTickets">929</td>
<td class="es-lastCell nowrap" id="se-103577925-priceRange"><span id="se-103577925-minPrice">$20.39</span>  to<br/><span id="se-103577925-maxPrice">$3,602.50</span></td>
</tr></tbody>
</table>

Answer 1

If length of the dfz dataframe is equal to length of the list, idlist .

You can remove the last for loop completely. Instead you can use

dfz["EventID"] = idlist

import pandas as pd
from bs4 import BeautifulSoup
import requests
import lxml.html as lh
import pprint
import re

with open("testfile.html") as f:
    data = f.read()
    soup = BeautifulSoup(data, 'lxml')
    pd.set_option('display.max_rows', 500)
    pd.set_option('display.max_columns', 500)
    pd.set_option('display.width', 1000)
    dfs = pd.read_html(soup.prettify())
    df = dfs[0]
    dfz=df.rename(columns = {'Event date  Time (local)':'EventDate'}).rename(columns = {'Event name  Venue':'EventName'}).rename(columns = {'Tickets  listed':'AmntTickets'}).rename(columns = {'Price  range':'PriceRange'}).rename(columns = {'Unnamed: 0':'EventID'})
    idlist = []
    for se in soup.find_all('span', id=re.compile(r'min')):
        se = (str(se))
        seeme1 = se.replace('<span id="se-','')
        seeme, sep, tail = seeme1.partition('-')
        idlist.append(seeme)
    dfz["EventID"] = idlist
    print(dfz)

Then you will get your dataframe you have requested.

     EventID                   EventDate                                          EventName  AmntTickets              PriceRange
0  103577924  Thu, 10/11/2018  8:20 p.m.  Philadelphia Eagles at New York Giants  MetLif...         6655  $134.50  to  $2,222.50
1  103577925  Thu, 10/11/2018  8:21 p.m.  PARKING PASSES ONLY Philadelphia Eagles at New...          929   $20.39  to  $3,602.50

If the dataframe dfz and the list idlist are of unequal length. And you can use the below code to append data for unequal length of lists.

import pandas as pd
from bs4 import BeautifulSoup
import requests
import lxml.html as lh
import pprint
import re

with open("testfile.html") as f:
    data = f.read()
    soup = BeautifulSoup(data, 'lxml')
    pd.set_option('display.max_rows', 500)
    pd.set_option('display.max_columns', 500)
    pd.set_option('display.width', 1000)
    dfs = pd.read_html(soup.prettify())
    df = dfs[0]
    dfz=df.rename(columns = {'Event date  Time (local)':'EventDate'}).rename(columns = {'Event name  Venue':'EventName'}).rename(columns = {'Tickets  listed':'AmntTickets'}).rename(columns = {'Price  range':'PriceRange'}).rename(columns = {'Unnamed: 0':'EventID'})
    idlist = []
    for se in soup.find_all('span', id=re.compile(r'min')):
        se = (str(se))
        seeme1 = se.replace('<span id="se-','')
        seeme, sep, tail = seeme1.partition('-')
        idlist.append(seeme)

    for ind, row in dfz.iterrows():
        try:
            dfz.EventID.iloc[ind] = idlist[ind]
        except Exception as e:
            pass
    print(dfz)