def find_user_matchIDs(username): 'search the target user latest 3page martch id' matchid=[] serverName=r'网通三' playerName=username matchId_by_name_url=r'http://lolbox.duowan.com/matchList.php?serverName=%s&playerName=%s'%(serverName,urllib.quote(playerName)) re=spider.http_header(matchId_by_name_url) html=urllib2.urlopen(re).read() soup_html=spider.BeautifulSoup(html,"html.parser") page_nnnumber=int(spider.get_page_limit(soup_html)) t=spider.find_match_id(soup_html) matchid.extend(t)#page_nnnumber默认从0开始,记录数据,避免后续重复查询 # print '第%s页有%s条数据,当前一共%s数据'%(1,len(t),len(matchid)) if page_nnnumber<=2: logging.DEBUG('%s 用户数据过少,不予统计'%(username)) return [] else: for n_page in range(1,4): matchId_by_name_url=r'http://lolbox.duowan.com/matchList.php?serverName=%s&playerName=%s&page=%s'%(serverName,playerName,str(n_page+1)) re=spider.http_header(matchId_by_name_url) html=urllib2.urlopen(re).read() soup_html=spider.BeautifulSoup(html,"html.parser") temp=spider.find_match_id(soup_html) matchid.extend(temp) # print '第%s页有%s条数据,当前一共%s数据'%(n_page+1,len(temp),len(matchid)) if len(matchid)>15: break return matchid
def find_user_matchIDs(username): 'search the target user latest 3page martch id' matchid = [] serverName = r'网通三' playerName = username matchId_by_name_url = r'http://lolbox.duowan.com/matchList.php?serverName=%s&playerName=%s' % ( serverName, urllib.quote(playerName)) re = spider.http_header(matchId_by_name_url) html = urllib2.urlopen(re).read() soup_html = spider.BeautifulSoup(html, "html.parser") page_nnnumber = int(spider.get_page_limit(soup_html)) t = spider.find_match_id(soup_html) matchid.extend(t) #page_nnnumber默认从0开始,记录数据,避免后续重复查询 # print '第%s页有%s条数据,当前一共%s数据'%(1,len(t),len(matchid)) if page_nnnumber <= 2: logging.DEBUG('%s 用户数据过少,不予统计' % (username)) return [] else: for n_page in range(1, 4): matchId_by_name_url = r'http://lolbox.duowan.com/matchList.php?serverName=%s&playerName=%s&page=%s' % ( serverName, playerName, str(n_page + 1)) re = spider.http_header(matchId_by_name_url) html = urllib2.urlopen(re).read() soup_html = spider.BeautifulSoup(html, "html.parser") temp = spider.find_match_id(soup_html) matchid.extend(temp) # print '第%s页有%s条数据,当前一共%s数据'%(n_page+1,len(temp),len(matchid)) if len(matchid) > 15: break return matchid
def find_mathID_detail(matchId,user_id): 'retrun find_users and detail_dat,the input match is the match id' serverName=r'网通三' playerName=user_id battle_url=r'http://lolbox.duowan.com/matchList/ajaxMatchDetail2.php?matchId=%s&serverName=%s&playerName=%s&favorate=0'%(matchId,urllib.quote(serverName),urllib.quote(playerName)) find_users=[] re=spider.http_header(battle_url) html=urllib2.urlopen(re).read() soup_html=BeautifulSoup(html,"html.parser") detail_dat=spider.battle_detail_parse(soup_html) if len(detail_dat)!=0: for item in detail_dat: find_users.append(item[0]) else: return find_users,detail_dat return find_users,detail_dat
def find_mathID_detail(matchId, user_id): 'retrun find_users and detail_dat,the input match is the match id' serverName = r'网通三' playerName = user_id battle_url = r'http://lolbox.duowan.com/matchList/ajaxMatchDetail2.php?matchId=%s&serverName=%s&playerName=%s&favorate=0' % ( matchId, urllib.quote(serverName), urllib.quote(playerName)) find_users = [] re = spider.http_header(battle_url) html = urllib2.urlopen(re).read() soup_html = BeautifulSoup(html, "html.parser") detail_dat = spider.battle_detail_parse(soup_html) if len(detail_dat) != 0: for item in detail_dat: find_users.append(item[0]) else: return find_users, detail_dat return find_users, detail_dat