爬取王者荣耀 和LOL
其他的我也不想多说
代码
import os,zipfile
import requests
'''
王者
'''
headers={
"Use-Agent":
"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Mobile Safari/537.36"
}
# 做出请求
def
start_request(
url):
request = requests.get(url,
headers=headers)
if request.status_code ==
200 :
return request.json()
def
save_img(
filename,
content):
with
open(filename,
'wb')
as
file:
file.write(content)
def
save_zip(
newpath,
path):
print(
"开始压缩文件")
with zipfile.ZipFile(newpath,
'w',zipfile.ZIP_DEFLATED)
as zp:
for path, fileparename, filename
in os.walk(path):
#path fileparename filename 路劲，文件夹名，文件名
for name
in filename:
zp.write(os.path.join(path,name))
# 把要压缩的文件写入压缩
print(
"压缩文件成功")
if
__name__ ==
'__main__':
url =
"http://pvp.qq.com/web201605/js/herolist.json"
img =
"http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/"
herojson = start_request(url)
num =
0
for i
in
range(
len(herojson)):
hero_code = herojson[i][
'ename']
hero_name = herojson[i][
'cname']
hero_skinlist =herojson[i][
'skin_name'].split(
'|')
# 文件夹不存在则创建
save_dir =
r
'E:
\p
ython
\p
ythonzong
\爬
虫
\r
equest
\i
mg
\%
s'%hero_name
if
not os.path.exists(save_dir):
os.mkdir(save_dir)
for j
in
range(
1,
len(hero_skinlist)+
1):
num +=
1
imgurl =img +
str(hero_code) +
'/' +
str(hero_code) +
'-bigskin-'+
str(j)+
'.jpg'
# 组装imgurl
request = requests.get(imgurl,
headers=headers)
filename =
'
{0}
\
{1}
.jpg'.format(save_dir,hero_skinlist[j-
1])
save_img(filename,request.content)
print(num)
print(
"爬取成功")
path=
r
"E:
\p
ython
\p
ythonzong
\爬
虫
\r
equest
\i
mg"
newpath=
r
"E:
\p
ython
\p
ythonzong
\爬
虫
\r
equest
\王
者荣耀img.zip"
save_zip(newpath,path)
import json
import os
import requests
headers = {
'User-Agent':
'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.7 Mobile Safari/537.36'}
num =
1
def
get_headers():
'''
得到json对象
'''
url =
'http://lol.qq.com/biz/hero/champion.js'
request = requests.get(url,
headers =headers)
jsontext = request.text[request.text.find(
'key')-
2:-
1]
# 得到标准的json字符串
jsons = json.loads(jsontext)
# 得到python对象
return jsons
'''
循坏组合成得到图片url
'''
def
get_imgurl(
jsons):
for valu
in jsons.get(
'keys').values():
hero_url =
'http://lol.qq.com/biz/hero/'+valu+
'.js'
# 得到英雄的详资源定位符
request = requests.get(hero_url,
headers =headers)
jsontext = request.text[request.text.find(
'data')-
2:-
1]
# 得到标准的json字符串
jsons = json.loads(jsontext)
# 得到python对象
# 根据英雄创建一个文件夹
filepaths =
r
'E:
\p
ython
\p
ythonAdvanced
\i
mgs
\%
s'%jsons.get(
'data').get(
'title')
if
not os.path.exists(filepaths):
os.mkdir(filepaths)
for item
in jsons.get(
'data').get(
'skins'):
yield {
'imgid':item.get(
'id'),
'num': item.get(
'num'),
'name':item.get(
'name'),
'filepaths':filepaths
}
def
save_img(
yields):
for item
in yields:
imgurl =
r
"http://ossweb-img.qq.com/images/lol/web201310/skin/big"+
str(item.get(
'imgid')) +
".jpg"
request = requests.get(imgurl,
headers =headers)
print(
'爬取
{0}
英雄的皮肤中...'.format(item.get(
'name')))
filename = item.get(
'filepaths')+
"
\\
" + item.get(
'name')+
".jpg"
with
open(filename,
'wb')
as
file:
file.write(request.content)
global num
num +=
1
if
__name__ ==
'__main__':
jsons = get_headers()
imgurls = get_imgurl(jsons)
save_img(imgurls)
print(
'爬取完毕，共爬取
{0}
张英雄皮肤'.format(num))