联盟王者

最新推荐文章于 2019-03-07 23:24:23 发布

?898

最新推荐文章于 2019-03-07 23:24:23 发布

阅读量435

点赞数

本文链接：https://blog.csdn.net/qq_17172105/article/details/53931890

版权

import os,requests,re,random
from bs4 import BeautifulSoup
def header():
headers = [
{"User-Agent": "Mozilla/5.0 (Android; Mobile; rv:27.0) Gecko/27.0 Firefox/27.0"},
{"User-Agent": "BlackBerry9700/5.0.0.862 Profile/MIDP-2.1 Configuration/CLDC-1.1 VendorID/331 UNTRUSTED/1.0 3gpp-gba"},
{"User-Agent": "Mozilla/5.0 (BlackBerry; U; BlackBerry 9930; en-US) AppleWebKit/534.11+ (KHTML, like Gecko) Version/7.0.0.241 Mobile Safari/534.11+"},
{"User-Agent": "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; zh-TW) AppleWebKit/534.8+ (KHTML, like Gecko) Version/6.0.0.448 Mobile Safari/534.8+"},
{"User-Agent": "Mozilla/5.0 (Linux; U; Android 4.0.4; en-gb; GT-I9300 Build/IMM76D) AppleWebKit/534.30 (KHTML, like Gecko) Version/4.0 Mobile Safari/534.30"},
{"User-Agent": "Mozilla/5.0 (Linux; U; Android 2.2; en-us; SCH-I800 Build/FROYO) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"},
{"User-Agent": "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"},
{"User-Agent": "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)"},
{"User-Agent": "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0; Touch)"},
{"User-Agent": "Mozilla/5.0(iPad; U; CPU iPhone OS 3_2 like Mac OS X; en-us) AppleWebKit/531.21.10 (KHTML, like Gecko) Version/4.0.4 Mobile/7B314 Safari/531.21.10"},
{"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 5_1 like Mac OS X) AppleWebKit/534.46 (KHTML, like Gecko) Version/5.1 Mobile/9B179 Safari/7534.48.3"},
{"User-Agent": "Opera/9.80 (J2ME/MIDP; Opera Mini/9.80 (J2ME/22.478; U; en) Presto/2.5.25 Version/10.54"},
{"User-Agent": "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_3; en-us; Silk/1.1.0-80) AppleWebKit/533.16 (KHTML, like Gecko) Version/5.0 Safari/533.16 Silk-Accelerated=true"},
{"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/537.13+ (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2"},
{"User-Agent": "Mozilla/5.0 (Linux; Android 4.4.4; Nexus 5 Build/KTU84P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.117 Mobile Safari/537.36"},
{"User-Agent": "Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Safari/535.19"},
{"User-Agent": "Mozilla/5.0 (MeeGo; NokiaN9) AppleWebKit/534.13 (KHTML, like Gecko) NokiaBrowser/8.5.0 Mobile Safari/534.13"},
{"User-Agent": "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/12.0.024; Profile/MIDP-2.1 Configuration/CLDC-1.1; en-us) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.12344"},
{"User-Agent": "Mozilla/5.0 (X11; U; Linux armv7l; no-NO; rv:1.9.2.3pre) Gecko/20100723 Firefox/3.5 Maemo Browser 1.7.4.8 RX-51 N900"},
{"User-Agent": "Mozilla/5.0 (PlayBook; U; RIM Tablet OS 2.0.1; en-US) AppleWebKit/535.8+ (KHTML, like Gecko) Version/7.2.0.1 Safari/535.8+"},
{"User-Agent": "Mozilla/5.0 (PLAYSTATION 3 4.60) AppleWebKit/531.22.8 (KHTML, like Gecko)"},
{"User-Agent": "Mozilla/5.0 (PlayStation Vita 3.12) AppleWebKit/536.26 (KHTML, like Gecko) Silk/3.2"},
{"User-Agent": "Mozilla/5.0 (Linux; Android 4.4.2; en-us; SAMSUNG SCH-I545 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Version/1.5 Chrome/28.0.1500.94 Mobile Safari/537.36"},
{"User-Agent": "Mozilla/5.0 (Linux; Android 4.1.2; GT-I8190 Build/JZO54K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.117 Mobile Safari/537.36"},
{"User-Agent": "Mozilla/5.0 (Linux; Android 4.4.2; en-gb; SAMSUNG SM-G900F Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Version/1.6 Chrome/28.0.1500.94 Mobile Safari/537.36"},
{"User-Agent": "Mozilla/5.0 (SAMSUNG; SAMSUNG-GT-S8530/S8530DDLC2; U; Bada/2.0; en-us) AppleWebKit/534.20 (KHTML, like Gecko) Dolfin/3.0 Mobile WVGA SMM-MMS/1.2.0 OPN-B"},
{"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:15.0) Gecko/20100101 Firefox/15.0.1"},
{"User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"},
{"User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; SAMSUNG; SGH-i917)"},
{"User-Agent": "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; ARM; Trident/6.0)"},
{"User-Agent": "Mozilla/5.0 (iPhone; U; CPU iPhone OS) (compatible; Googlebot-Mobile/2.1; http://www.google.com/bot.html)"},
{"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10A5376e Safari/8536.25 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"},
{"User-Agent": "DoCoMo/2.0 N905i(c100;TB;W24H16) (compatible; Googlebot-Mobile/2.1; +http://www.google.com/bot.html)"},
{"User-Agent": "SAMSUNG-SGH-I617/UCHJ1 Mozilla/4.0 (compatible; MSIE 6.0; Windows CE; IEMobile 7.11)"},
{"User-Agent": "Mozilla/4.0 (compatible; MSIE 6.0; Windows CE; IEMobile 8.12; MSIEMobile 6.0) 320x240; VZW; UTStar-XV6175.1; Windows Mobile 6.5 Standard;"},
{"User-Agent": "Opera/9.80 (Android 2.3.3; Linux; Opera Mobi/ADR-1202011015; U; en) Presto/2.9.201 Version/11.50"}

]
return random.choice(headers)

start_url='http://www.laoyuegou.com/x/zh-cn/lol/lol/godrank.html'
s=requests.Session()
if not os.path.isdir('d://王者排名'):
os.mkdir('d://王者排名')

data=s.get(start_url,headers=header()).content.decode('utf-8')
bs=BeautifulSoup(data,'lxml')
bs=bs.find_all("div","fliter-val")

def parser(area_link,area_name):
links=[area_link+'&pageta=%d'%i for i in range(2,8)]
links.insert(0,area_link)
t='d://王者排名//%s.txt'%area_name
if not os.path.isfile(t):
for link in links:
content=s.get(link,headers={**header(),**{'Referer':link}}).content.decode('utf-8')
bs=BeautifulSoup(content,'lxml')
bs=bs.find("article","table table-wangzhe")
bs=bs.find_all("div","row")
for items in bs:
player={}
player['排名']=items.find("div","item1").text[1:].strip()
player['玩家']=items.find("div","item2").text.replace('\n','')
player['段位胜点']=items.find("div","item3").text.strip()
player['胜率']=items.find("div","item4").text.replace('\n','')
player['擅长_位置']=items.find("div","item6").text.strip()
x=items.find("div","item7 common-role")
player['本命英雄']=[i.get("alt") for i in x.find_all("img")]
player_info=sorted(player.items(), key=lambda player:player[0])
with open(t,'a',errors='replace') as f:
f.write(str(player_info)+'\n')

for bsi in bs[:3]:
areas=bsi.find("ul","select")
areas=areas.find_all("li")
for area in areas:
area_name=area.text.strip()
area_link=area.a.get('href').strip()
print(area_name,area_link)
parser(area_link,area_name)