[Python] 纯文本查看 复制代码
import random
import requests
from bs4 import BeautifulSoup
import os
import time
import json
import threading
user_agent = [
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
# iPhone 6
"Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",
# 新版移动ua
"Mozilla/5.0 (Linux;u;Android 4.2.2;zh-cn;) AppleWebKit/534.46 (KHTML,like Gecko) Version/5.1 Mobile Safari/10600.6.3 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"
]
# 随机获取一个请求头
def get_headers():
return {'User-Agent': random.choice(user_agent)}
index = 'http://www.netbian.com' # 网站根地址
interval = 0.1 # 爬取图片的间隔时间
firstDir = 'e:/bian' # 总路径
classificationDict = {} # 存放网站分类子页面的信息
def ui():
print('--------------netbian-------------')
print('全部', end=' ')
for c in classificationDict.keys():
print(c, end=' ')
print()
choice = input('请输入分类名：')
if(choice == '全部'):
for c in classificationDict.keys():
select_classification(c)
elif(choice not in classificationDict.keys()):
print("输入错误，请重新输入！")
print('----')
ui()
else:
print('---------------------------')
print('--------------' + choice + '-------------')
print('---------------------------')
secondUrl = classificationDict[choice]['url']
secondDir = classificationDict[choice]['path']
select = '#main > div.page > span.slh'
pageIndex = screenPage(secondUrl, select)
lastPagenum = int(pageIndex) # 获取最后一页的页码
for i in range(0, lastPagenum):
if i == 0:
save_list(secondUrl)
else:
save_list(secondUrl+ 'index_%d.htm' % (i + 1))
print('--------------' + choice + ': ' + str(i + 1) + '-------------')
def screen(url, select):
headers = get_headers() # 随机获取一个headers
html = requests.get(url = url, headers = headers)
html.encoding = 'gbk' # 网站的编码
html = html.text
soup = BeautifulSoup(html, 'lxml')
return soup.select(select)
def init_classification():
url = index
select = '#header > div.head > ul > li:nth-of-type(1) > div > a'
classifications = screen(url, select)
for c in classifications:
href = c.get('href') # 获取的是相对地址
text = c.string # 获取分类名
if(text == '4k壁纸'): # 4k壁纸，因权限问题无法爬取，直接跳过
continue
secondDir = firstDir + '/' + text # 分类目录
url = index + href # 分类子页面url
global classificationDict
classificationDict[text] = {
'path': secondDir,
'url': url
}
def screenPage(url, select):
html = requests.get(url = url, headers = get_headers())
html.encoding = 'gbk'
html = html.text
soup = BeautifulSoup(html, 'lxml')
return soup.select(select)[0].next_sibling.text
def save_list(result):
""" 保存结果 """
with open('result.json','a',encoding='utf-8') as f:
f.write(json.dumps(result,ensure_ascii=False))
f.close()
def downloadpic(link):
href = link.get('href')
if(href == 'http://pic.netbian.com/'): # 过滤图片广告
return
# 第一次跳转
if('http://' in href): # 有极个别图片不提供正确的相对地址
url = href
else:
url = index + href
select = 'div#main div.endpage div.pic div.pic-down a'
link = screen(url, select)
if(link == []):
print(url + ' 无此图片，爬取失败')
return
href = link[0].get('href')
# 第二次跳转
url = index + href
# 获取到图片了
select = 'div#main table a img'
link = screen(url, select)
if(link == []):
print(url + " 该图片需要登录才能爬取，爬取失败")
return
name = link[0].get('alt').replace('\t', '').replace('|', '').replace(':', '').replace('\\', '').replace('/', '').replace('*', '').replace('?', '').replace('"', '').replace('<', '').replace('>', '')
print(name) # 输出下载图片的文件名
src = link[0].get('src')
if(requests.get(src).status_code == 404):
print(url + ' 该图片下载链接404，爬取失败')
return
response = requests.get(src)
path2 =r'e:\bian\\'+ name + '.jpg'
with open(path2, 'wb') as pic:
for chunk in response.iter_content(128):
pic.write(chunk)
time.sleep(interval)
def download(url):
select = 'div#main div.list ul li a'
links = screen(url, select)
threads = []
for link in links:
t = threading.Thread(target=downloadpic,args=(link,))
t.start()
threads.append(t)
for t in threads:
t.join()
def main():
init_classification()
ui()
with open('result.json','r') as f:
line = f.read().strip()
linestr = line.split("\"")
while '' in linestr:
linestr.remove('')
for url in linestr:
download(url)
if __name__ == '__main__':
main()
发表于 2020-5-25 20:45
|
发表于 2020-5-25 20:56
