def fetchAlbum(url):
pq = helper.get(url)
dirName = os.path.join('.', 'aiss', pq('title').text())
helper.mkDir(dirName)
index = 1
for img in pq('.message > img'):
helper.downloadImg(img.get('src'),
os.path.join(dirName, '%03d.jpg' % index))
index += 1
def fetchAlbum(url, dirName):
if 'rosi' in url:
pq = helper.get(url)
dirName = os.path.join(dirName,
pq('#post-title').text().split('No.')[1])
helper.mkDir(dirName)
for a in pq('.gallery-icon > a'):
imgUrl = a.get('href')
helper.downloadImg(imgUrl,
os.path.join(dirName,
imgUrl.split('/')[-1]))
def fetchPage(page):
url = '%s/page/%d/' % (BASE_URL, page)
pq = helper.get(url)
for a in pq('a.disp_a'):
title = a.get('title').replace('Permalink to ', '')
url = a.get('href')
dirName = os.path.join('cartoon', title)
if not os.path.exists(os.path.join(dirName, 'url.txt')):
helper.mkDir(dirName)
if not fetchGallery(url, title, page):
return False
return True
def fetchComic(webPage, comicIndex, url, page = 1, comicDir = None):
pq = helper.get('%s/%d' % (url, page))
if page == 1:
title = pq('title').text().replace('/', '&').split(' - ')[0]
comicDir = os.path.join('animezilla', title)
if os.path.exists(os.path.join('animezilla', '0uploaded', title, 'done.txt')):
return True
if os.path.exists(os.path.join(comicDir, 'done.txt')):
return True
helper.mkDir(comicDir)
if webPage == 1 and comicIndex == 16:
if page < 90:
return fetchComic(webPage, comicIndex, url, 90, comicDir)
img = pq('img#comic')
print('[%s] downloading webPage page => %d, comic index => %d, comic page => %d' % (helper.now(), webPage, comicIndex, page))
downloadImg(img.attr('src'), os.path.join(comicDir, '%03d.jpg' % page), url)
time.sleep(3)
if(len(img.parents('a')) == 0):
helper.writeFile('done', os.path.join(comicDir, 'done.txt'))
return True
return fetchComic(webPage, comicIndex, url, page + 1, comicDir)
def fetch_model(url, name, head_img):
'''fetch model'''
model_dir = os.path.join('vivthomas', 'model')
helper.mkDir(model_dir)
helper.mkDir(os.path.join('vivthomas', 'photo'))
# 下载头像先
helper.downloadImg(head_img, os.path.join(
model_dir, '%s.jpg' % name))
if os.path.exists(os.path.join('vivthomas', 'model', '%s.json' % (name))):
return
# 然后去抓取详细数据
model_info = {
'name': name,
'photos': []
}
pyquery = helper.get(url)
country_span = pyquery('.custom-country')
model_info['country'] = country_span.text() if country_span else 'unknow'
# 获取照片数据
custom_content_list = pyquery('.custom-content-list')
custom_content = None
for item in custom_content_list:
if item.getchildren()[0].getchildren()[0].text.startswith('Photos with'):
custom_content = item
break
# if item.getchildren()[0].getchildren()[0].text:
# pass
if custom_content is None:
helper.writeFile(json.dumps(model_info), os.path.join(
'vivthomas', 'model', '%s.json' % (name)))
return
# if len(custom_content_list) == 3:
# custom_content = custom_content_list[1]
# else:
# custom_content = custom_content_list[0]
list_group_item_list = custom_content.getchildren()[2].findall('li')
for list_group_item in list_group_item_list:
custom_list_item_detailed = list_group_item.getchildren()[1]
img = custom_list_item_detailed.getchildren()[0].getchildren()[
0].getchildren()[0]
# custom_list_item_detailed.getchildren()[1].getchildren()[0].getchildren()[0].text
photo_name = img.get('alt')
# Released: Feb 26, 2016
date_str = custom_list_item_detailed.getchildren()[1].getchildren()[
1].text_content().split(': ')[1]
date_str = '%s-%d-%s' % (date_str.split(', ')[1], helper.getMonth(
date_str.split(' ')[0]), date_str.split(' ')[1].replace(',', ''))
# 模特名
arr = custom_list_item_detailed.getchildren()[1].getchildren()[
2].getchildren()
model_name_arr = []
for i in xrange(1, len(arr)):
model_name_arr.append(arr[i].text)
# model_name = custom_list_item_detailed.getchildren()[1].getchildren()[2].getchildren()[1].text
# print(model_name_arr)
# date = datetime.datetime(int(date_str.split(', ')[1]), helper.getMonth(date_str.split(' ')[0]), int(date_str.split(' ')[1].replace(',', '')))
# print date
# 下载照片的封面
photo_path = os.path.join('vivthomas', 'photo', '%s_%s' % (date_str, photo_name.replace(
'/', ' ')), '%s_%s.jpg' % (date_str, photo_name.replace('/', ' ')))
helper.downloadImg(img.get('src'), photo_path)
# 存到数据库
# mongo.newAlbun(photo_name, date)
photo_json = {
'date': date_str,
'name': photo_name,
'model': model_name_arr
}
photo_json_str = json.dumps(photo_json)
model_info.get('photos').append(photo_json)
helper.writeFile(photo_json_str, os.path.join(
'vivthomas', 'photo', '%s_%s' % (date_str, photo_name), '%s_%s.json' % (date_str, photo_name)))
helper.writeFile(json.dumps(model_info), os.path.join(
'vivthomas', 'model', '%s.json' % (name)))
except Exception as e:
print(e)
return
with open(imgPath, 'wb') as f:
for chunk in r.iter_content(chunk_size=1024):
if chunk:
f.write(chunk)
f.flush()
if __name__ == '__main__':
baseUrl = 'http://www.hhssee.com/manhua31358.html'
pq = helper.get(baseUrl)
comicName = pq('h1').text()
comicDir = os.path.join('hhssee', comicName)
helper.mkDir(comicDir)
bookUrlArr = []
for a in pq('a.l_s'):
bookUrlArr.append({
'url': 'http://www.hhssee.com%s' % a.get('href'),
'name': a.text
})
bookIndex = 0
for bookData in bookUrlArr:
bookIndex += 1
# if bookIndex < 5:
# continue
bookName = bookData.get('name')
if not '卷' in bookName:
import helper
import re, os, calendar, datetime
# http://madamevoyeur.com/index.php?p=1&a=2010
BASE_URL = 'http://madamevoyeur.com'
# def fetchImagePage(year, pageIndex):
# url = 'http://madamevoyeur.com/index.php?p=365&a=2016'
# pq = helper.get(url)
# pq("a[name='%s']>video" %CateGory)
# for item in pq(paramter):
if __name__ == '__main__':
dirName = 'madameVoyeur'
helper.mkDir(dirName)
t = datetime.datetime.now()
nowYear = int(t.year)
year = 2017
while year <= nowYear:
pageIndex = 24
for pageIndex in range(1, calendar.isleap(year) and 367 or 366):
print('%s => year: %d page: %d' % (helper.now(), year, pageIndex))
# http://madamevoyeur.com/images/2016/16035.jpg
helper.downloadImg('%s/images/%d/%02d%03d.jpg' % (BASE_URL, year, 0 if year == 2010 else year - 2000, pageIndex), os.path.join(dirName, '%d_%03d_1.jpg' % (year, pageIndex)))
helper.downloadImg('%s/images/%d-2/%02d%03d.jpg' % (BASE_URL, year, 0 if year == 2010 else year - 2000, pageIndex), os.path.join(dirName, '%d_%03d_2.jpg' % (year, pageIndex)))
helper.downloadImg('%s/images/%d-3/%02d%03d.jpg' % (BASE_URL, year, 0 if year == 2010 else year - 2000, pageIndex), os.path.join(dirName, '%d_%03d_3.jpg' % (year, pageIndex)))
year += 1
# year 2017 page 24
def fetchGallery(url, page):
print('now page %d' % page)
pq = helper.get(url)
# SexArt – Alexis Crystal & Michael Fly – Call | AdultPhotoSets.ru
title = pq('title').text()
title = title.split(' | ')[0]
dirName = os.path.join('imgs', '0uploaded', title)
dirName = filterDirName(dirName)
if os.path.exists(dirName):
print('exists!!! skip!')
return True
dirName = os.path.join('imgs', '0uploaded', '0baidu', title)
dirName = filterDirName(dirName)
if os.path.exists(dirName):
print('exists!!! skip!')
return True
dirName = os.path.join('imgs', '0uploaded', 'MetArt', title)
dirName = filterDirName(dirName)
if os.path.exists(dirName):
print('exists!!! skip!')
return True
dirName = os.path.join('imgs', '0nas', 'MetArt', title)
dirName = filterDirName(dirName)
if os.path.exists(dirName):
print('exists!!! skip!')
return True
dirName = os.path.join('imgs', '0nas', 'MetArtX', title)
dirName = filterDirName(dirName)
if os.path.exists(dirName):
print('exists!!! skip!')
return True
dirName = os.path.join('imgs', '0error', title)
dirName = filterDirName(dirName)
if os.path.exists(dirName):
print('exists!!! skip!')
return True
# 创建本地目录
dirName = os.path.join('imgs', title)
dirName = filterDirName(dirName)
# print('make dir %s' % dirName)
# 如果存在url.txt，说明这个相册已经抓取过了，直接return吧
if os.path.exists('%s/url.txt' % dirName):
print('exists!!! skip!')
return True
helper.mkDir(dirName)
i = 0
tag = None
imgUrl = []
aArr = pq('a.externalLink')
if not aArr or len(aArr) < 1:
aArr = pq('div.content>p>a')
if not aArr or len(aArr) < 1:
aArr = pq('div.content>a')
if not aArr or len(aArr) < 1:
# http://imgtrex.com/8kbfdzphqsr1/daniela-dressed-for-sex-02-10000px
arr = re.compile(r'http://imgtrex\.com/\w+/[a-z0-9-]+\.jpg').findall(pq.html())
if len(arr) == 0:
print('can\'t find any <a>')
if url == 'http://adultphotosets.ru/met-art-lupita-gifera/':
return True
if url == 'http://adultphotosets.ru/rylskyart-oretha-mars-second-2-mars/':
return True
if url == 'http://adultphotosets.ru/met-art-nikolina-deirth/':
return True
return False
aArr = [{'href': a} for a in arr]
# for a in arr:
# aArr.append({'href': a})
if aArr and len(aArr) > 0:
if 'imgchili.net' in aArr[0].get('href'):
imgArr = pq('div.content>p>a>img')
if not imgArr or len(imgArr) < 1:
imgArr = pq('div.content>a>img')
# http://t10.imgchili
if imgArr and len(imgArr) > 0:
tag = imgArr[0].get('src').replace('http://', '').split('.imgchili')[0].replace('t', '')
for a in aArr:
print('%s image index => %d' % (helper.now(), i))
url = fetchLargeImageUrl(a.get('href'), tag)
if url == None:
if i == 0:
print('fetchLargeImageUrl failed')
return True
else:
if url != '':
imgUrl.append(url)
i += 1
if len(imgUrl) > 0:
helper.writeFile('\n'.join(imgUrl), '%s/url.txt' % dirName)
return True
def fetchModel(url=None, headUrl=None, name='Abril C', score=8.97):
if url is None:
url = 'https://www.eternaldesire.com/model/abril-c/'
if headUrl is None:
headUrl = 'https://static.eternaldesire.com/media/headshots/abril-c.jpg?fv=e6f189022422389d377149f795d1da13'
modelPath = os.path.join('eternaldesire', 'models', name)
helper.mkDir(modelPath)
helper.downloadImg(headUrl,
os.path.join(modelPath, '%s_EternalDesire.jpg' % name))
modelInfo = {
'name': name,
'score': score,
'Age first shot': 0,
'Eye color': '',
'Hair color': '',
'Breasts': '',
'Shaved': '',
'Measurements': '',
'Height': '',
'Weight': '',
'Country': '',
'Ethnicity': '',
'photos': []
}
pq = helper.get(url, None, None, 1)
infoLiArr = pq('.model_info > ul > li')
for li in infoLiArr:
arr = li.text_content().split(': ')
for key in modelInfo:
if key == arr[0]:
modelInfo[key] = arr[1]
break
photoIndex = 1
while photoIndex < 100:
photoDivArr = pq('#latest_photo_update_%d .update_cell' % photoIndex)
liArr = pq('#latest_photo_update_%d .hover_container_stats li' %
photoIndex)
if not liArr or len(liArr) == 0:
break
for i in xrange(0, len(photoDivArr)):
photoInfo = {'name': '', 'date': '0.0.1970', 'model': ''}
img = photoDivArr[i].find('a').find('img')
coverUrl = img.get('src')
photoInfo['name'] = img.get('alt')
photoInfo['date'] = liArr[i * 3].text_content().replace(
'Date published:', '')
photoInfo['model'] = liArr[i * 3 + 1].text_content().replace(
'Featuring: ', '')
jsonStr = json.dumps(photoInfo)
photoPath = os.path.join(
'eternaldesire', 'photos',
photoInfo.get('name') + '-' + photoInfo['model'])
helper.mkDir(photoPath)
helper.writeFile(jsonStr, os.path.join(photoPath, 'info.json'))
helper.downloadImg(
coverUrl,
os.path.join(
photoPath,
'%s_cover_EternalDesire.jpg' % photoInfo.get('name')))
modelInfo['photos'].append(photoInfo)
photoIndex += 1
helper.writeFile(json.dumps(modelInfo),
os.path.join(modelPath, 'info.json'))
import flightclub
import stockx
import goat
import nike
import kickz
import sys
# WEB_DOMAIN = ['footlocker', 'jimmyjazz', 'sneakersnstuff', 'footaction']
WEB_DOMAIN = ['finishline', 'champssports', 'stadiumgoods',
'flightclub', 'eastbay', 'stockx', 'goat', 'kickz', 'footlocker',
'nike', 'jimmyjazz']
if __name__ == '__main__':
for dir_name in WEB_DOMAIN:
helper.mkDir(os.path.join('.', 'imgs', dir_name))
parser = argparse.ArgumentParser()
parser.add_argument("target", help=','.join(WEB_DOMAIN))
parser.add_argument("action", help='common or hot')
options = parser.parse_args()
target = options.target
action = options.action
if target not in WEB_DOMAIN:
print('legal target: [%s] ' % ', '.join(WEB_DOMAIN))
else:
if target == 'eastbay':
eastbay.start(action)
elif target == 'footlocker':
footlocker.start(action)
elif target == 'jimmyjazz':
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# 生成缩略图，以供上传到qq群文件里
import Image, os, helper
dir_name = r'G:\adultphotosets\imgs\EternalDesire – Abril C – Turgues'.decode(
'utf-8')
def scale(imgPath):
print('try to open file: %s' % imgPath)
im = Image.open(imgPath)
# 获得图像尺寸:
w, h = im.size
im.thumbnail((200, int(h * 200 / w)))
# 把缩放后的图像用jpeg格式保存:
arr = imgPath.split('\\')
arr.insert(-1, 's')
im.save('\\'.join(arr), 'jpeg')
print('saved => %s' % '\\'.join(arr))
if __name__ == '__main__':
helper.mkDir(os.path.join(dir_name, 's'))
for parent, dirnames, filenames in os.walk(dir_name):
for filename in filenames:
if not parent.endswith('\\s'):
if filename.endswith('jpg'):
scale(os.path.join(parent, filename))
import json
import datetime
import helper
modelArr = []
albumArr = []
# def findModel(id):
# global modelArr
# for model in modelArr:
# if model.get('id') == id:
# return model
if __name__ == '__main__':
model_dir = '/Users/eddie104/Documents/hongjie/photosets/femjoy/model'
helper.mkDir(model_dir)
page = 1
while True:
url = 'https://www.femjoy.com/api/v2/actors?sorting=date&thumb_size=355x475&limit=48&page=%d' % page
txt = helper.get(url, returnText=True)
jsonData = json.loads(txt)
total_pages = jsonData.get('pagination').get('total_pages')
for modelData in jsonData.get('results'):
model = {
'id':
modelData.get('id'),
'slug':
modelData.get('slug'),
'name':
modelData.get('name'),