python3讀取BJDA藥品經營企業資料

標籤：decode   指定   com   pat   port   ubi   企業   txt   content   

#-*- coding:utf-8 -*- #讀取北京FDA的藥品經營企業資料# 20161125 zhangshaohuaimport reimport urllib.requestimport urllib.parseimport osdef getContent(url,pat,charSet):    #指定網址、Regex、編碼方式，返回指定內容    page = urllib.request.urlopen(url)    content = page.read().decode(charSet)    pattern = re.compile(pat)    result = re.findall(pattern,content)    return result#讀取首頁url = ‘http://www.bjda.gov.cn/eportal/ui?pageId=331148‘#取總記錄數,每頁20條zjls = getContent(url,‘總記錄數:(\d{1,5}),‘,‘UTF-8‘)vdzjls = int(zjls[0])vdzjls = int(round(vdzjls/20,0)) for i in range(51,vdzjls):    url = ‘http://www.bjda.gov.cn/eportal/ui?pageId=331148&currentPage=‘+str(i)    pattern = ‘artileId=(.*)">查看‘    page_id = getContent(url,pattern,‘UTF-8‘)    for url_id in page_id:        try:            subid = url_id            suburl = "http://www.bjda.gov.cn/eportal/ui?pageId=331631&artileId="+subid            qymc = getContent(suburl,‘企業名稱:</th>\r\n.*?<td>(.*?)</td>‘,‘UTF-8‘)            zcdz = getContent(suburl,‘登入位址:</th>\r\n.*?<td>(.*?)\s{0,3}</td>‘,‘UTF-8‘)            xkzh = getContent(suburl,‘許可證號:</th>\r\n.*?<td>(.*?)</td>‘,‘UTF-8‘)            print(qymc,zcdz,xkzh)            file_object = open(‘bjda.txt‘,‘a‘)                        file_object.write(qymc[0])            file_object.write(‘,‘)            file_object.write(zcdz[0])            file_object.write(‘,‘)                        file_object.write(xkzh[0])            file_object.write(‘\n\r‘)                    finally:            None        file_object.close()vdzjls  = int(zjls[0])print(‘藥品零售企業讀取完成！‘)

　　經曆了讀取HDA的練習，此次讀取BJ的資料開始比較順暢。在讀取996條資料時出錯，再次出現換行造成的問題；

多次試錯後用‘\s{0,3}’成功解決.

Regex要繼續學習，才能不斷進步，避免遇“”坑“”時能順利通過！

python3讀取BJDA藥品經營企業資料