Question

from bs4 import BeautifulSoup
import urllib
import json
import os

jaren = [str("2012"), str("2010"), str("2006"), str("2003"),str("2002"), str("1998"), str("1994"), str("1989"), str("1986"), str("1982"), str("1981"), str("1977"), str("1972"), str("1971"), str("1967"), str("1963"), str("1959"), str("1956")]
DESIRED_COLUMNS = {1, 2, 5} #scrapes only afk, aantal & zetels
verkiezingsData = []

filename = raw_input('Enter a filename: ') or 'data.json'

#open file and open json array
with open(filename, "w") as file:
   file.write("[{")
for Jaargetal in jaren:

     #url source 
     r = urllib.urlopen("http://www.nlverkiezingen.com/TK" + Jaargetal +".html").read()
     soup = BeautifulSoup(r, "html.parser")
     tables = soup.find_all("table")
     for table in tables:
         header = soup.find_all("h1")[0].getText()

         #print header
         with open(filename, "a+") as file:
              file.write("\"%s\": [" % header) #header as beginning json
         trs = table.find_all("tr")[0].getText()
         del verkiezingsData[:] #clear list before adding new data


         #add the 3 columns to a list
         for tr in table.find_all("tr")[:22]: #22 aantal columns van top till bottom
             for index, val in enumerate(tr.find_all('td')):
                  if index in DESIRED_COLUMNS: #linkt naar desired columns bovenin
                      verkiezingsData.append(val.getText().strip())


         #json array van de 3 vallues
         for a, b, c in zip(verkiezingsData[::3],        verkiezingsData[1::3], verkiezingsData[2::3]): #link naar desired columns 1,2,5
             data2 = {'afk':a,"aantal":b, "zetels":c}

             #file writing
             with open(filename, 'a') as outfile:
                 json.dump(data2, outfile)
                    outfile.write(",")


        #open file, delete last comma and close array
        with open(filename, 'ab+') as file:
                file.seek(-1, os.SEEK_END)
                file.truncate()
                file.write("],")

#open file, delete last comma, and close array
with open(filename, 'r+b') as file:
    file.seek(-1, os.SEEK_END)
    file.truncate()
    file.write("}]")

#open file and pretty print json data
with open(filename, 'r') as file:
    prettydata = json.load(file)
with open(filename, 'w') as file:
    json.dump(prettydata, file, sort_keys=True, indent=4, separators=(',', ': '))

我从nlverkiezingen.com上刮了一个刮刀

当它保存为json文件时：

"Tweede-Kamerverkiezingen - 12 september 2012": [
            {
                "aantal": "Aantal",
                "afk": "Afk.",
                "zetels": "Zetels"
            },
            {
                "aantal": "2504948",
                "afk": "VVD",
                "zetels": "41"
            },

第一行是：Aantal / Afk / Zetels。我不希望这个被刮掉。

我该如何更改？刮取从第二行开始

第二件事是，最后一行到处都是不同的。有时是第20排，第15排。

我该如何更改？当刮刮时看到白色/空行时刮削结束了吗？

Answer 1

不知道是否正确，这只是一个猜测，但可能像

for tr in table.find_all("tr")[1:22]

跳过第一行？

Answer 2

第一行是：Aantal / Afk / Zetels。我不希望这件事被刮掉。

替换 for tr in table.find_all("tr")[1:22]: 1

Python具有从零开始的索引，因此 指的是表中的第二行。

我该怎么改变？当刮刮时看到白色/空行时刮削结束了吗？

空表单元格中的u"\xa0"将由BeautifulSoup解析为@Override public View getView(int position, View convertView, ViewGroup parent) { // Get the data item for this position LockListDataModel locks = getItem(position); // Check if an existing view is being reused, otherwise inflate the view ViewHolder viewHolder; // view lookup cache stored in tag if (convertView == null) { viewHolder = new ViewHolder(); LayoutInflater inflater = LayoutInflater.from(getContext()); convertView = inflater.inflate(R.layout.list_row, parent, false); viewHolder.lockName = (TextView) convertView.findViewById(R.id.lockName); viewHolder.colour = (ImageView) convertView.findViewById(R.id.list_image); convertView.setTag(viewHolder); } else { viewHolder = (ViewHolder) convertView.getTag(); }// Populate the data into the template view using the data object viewHolder.lockName.setText(locks.lockName); viewHolder.colour.setVisibility(View.VISIBLE); viewHolder.colour.setBackground(ResourcesCompat.getDrawable(getContext().getResources(), R.drawable.time_profile_shape, null)); LayerDrawable shape = (LayerDrawable) ContextCompat.getDrawable(getContext(),R.drawable.time_profile_shape); GradientDrawable color = (GradientDrawable)(shape.findDrawableByLayerId(R.id.time_profile_lock_colour)); color.setColor(Color.parseColor(locks.color)); // Return the completed view to render on screen return convertView; } Python字符串。检查每行上第一个标记的内容，并将其与该值进行比较，并使用它来打破循环。

刮擦数据＆gt;停在白线

2 个答案: