日本語のURLのスクレイピング方法(Python2.7)

Python2.7の日本語スクレイピング方法があったので、使ってみた。

qiita.com

引数は読み込み用のcsvファイルを使用する。(1列目はURL)
openをcloseする必要がある気がする。

# coding:utf-8
import requests
from bs4 import BeautifulSoup
import csv
import sys
import urllib
from urlparse import urlparse


csv_reader = csv.reader(open(
    sys.argv[1], "rb"), delimiter=",", quotechar='"')

with open('[書き込み用csvファイル]', 'awb') as f:
    for row in csv_reader:
        csvWriter = csv.writer(f)
        try:
            if row[0] == "":
                csvWriter.writerow([i for i in row])
                continue
            p = urlparse(row[0])
            query = urllib.quote_plus(p.query, safe='=&')
            row[0] = '{}://{}{}{}{}{}{}{}{}'.format(
                p.scheme, p.netloc, p.path,
                ';' if p.params else '', p.params,
                '?' if p.query else '', query,
                '#' if p.fragment else '', p.fragment)
            r = requests.get(row[0])
            soup = BeautifulSoup(r.text.encode(r.encoding))
            result = soup.find(id='resultsGoodsPagingResultsShow')
            listdata = [i for i in row]
            listdata.append(result.text.encode('utf-8').strip())
            csvWriter.writerow(listdata)

        except Exception as e1:
            try:
                p = urlparse(row[0])
                query = urllib.quote_plus(p.query, safe='=&')
                row[0] = '{}://{}{}{}{}{}{}{}{}'.format(
                    p.scheme, p.netloc, p.path,
                    ';' if p.params else '', p.params,
                    '?' if p.query else '', query,
                    '#' if p.fragment else '', p.fragment)
                r = requests.get(row[0])
                soup = BeautifulSoup(r.text.encode(r.encoding))
                message = soup.find(id='errors').find('li')
                listdata = [i for i in row]
                listdata.append(message.text.encode('utf-8'))
                csvWriter.writerow(listdata+[e1])

            except Exception as e2:
                listdata = [i for i in row]
                csvWriter.writerow([i for i in row]+[e2])