def fetchLargeImageUrl(imgUrl, tag):
if not imgUrl.endswith('zip'):
if 'imagehosting.pro' in imgUrl or 'gif-jpg.com' in imgUrl or 'ipics.info' in imgUrl:
pq = helper.get(imgUrl)
img = pq('img.centred')
url = img.attr('src')
if not url:
img = pq('img.centred_resized')
url = img.attr('src')
if url == None:
return ''
return url
elif 'img.yt' in imgUrl or 'imgcandy.net' in imgUrl:
if 'img.yt' in imgUrl:
imgUrl = imgUrl.replace('http:', 'https:')
pq = helper.post(imgUrl, 2)
img = pq('img.centred')
return img.attr('src')
elif 'imgchili.net' in imgUrl:
# global imgchili_cookies
# pq = helper.get(imgUrl, imgchili_cookies)
# img = pq('img#show_image')
# url = img.attr('src')
# return url
# http://imgchili.net/show/102747/102747596__sexart_raddia_cover.jpg
# http://i11.imgchili.net/102747/102747596__sexart_raddia_cover.jpg
url = imgUrl.replace('//imgchili', '//i%s.imgchili' % tag).replace('show/', '')
return url
elif 'imagetwist.com' in imgUrl:
pq = helper.get(imgUrl)
if not pq:
return ''
img = pq('img.img-responsive')
url = img.attr('src')
return url or ''
elif 'dfiles.ru' in imgUrl:
# 这是个提供下载zip的页面，直接跳过
return ''
elif 'imgtrex.com' in imgUrl:
pq = helper.get(imgUrl)
img = pq('img.pic')
return img.attr('src')
elif 'addimage.info' in imgUrl:
print('addimage.info is over!!!')
return ''
elif 'dragimage.org' in imgUrl:
print('dragimage.org is over!!!')
return ''
else:
print('unknow image url => %s' % imgUrl)
return None
return ''
def fetch_detail(url):
url = 'https://www.footaction.com' + url
pq = helper.get(url, cookies)
name = pq('span.c-product-name').text()
print('name = %s' % name)
number = pq('div.c-tab-panel').text().split(' ')[2]
print('number = %s' % number)
size_price_arr = []
price = '0.00'
try:
price = float(pq('span.sr-only').text().replace('$', ''))
except:
price = float(pq('span.final').text().replace('$', ''))
size_arr = pq('div.c-size p > label').text().split(' ')
for size in size_arr:
size_price_arr.append({
'size': float(size),
'price': price,
'isInStock': True
})
print('size_price_arr = ', size_price_arr)
img_json_str = helper.get('https://images.footaction.com/is/image/EBFL2/%sMM?req=set,json' % number, returnText=True)
img_json = None
img_url = None
try:
img_json = json.loads(img_json_str.replace('/*jsonp*/s7jsonResponse(', '').replace(',"");', ''))
img_item_arr = img_json.get('set').get('item')
for img_item in img_item_arr:
if img_item.get('type') == 'img_set':
img_url = img_item.get('set').get('item')[0].get('s').get('n')
break
except:
img_json_str = helper.get('https://images.footaction.com/is/image/EBFL2/%s?req=set,json' % number, returnText=True)
img_json = json.loads(img_json_str.replace('/*jsonp*/s7jsonResponse(', '').replace(',"");', ''))
img_item_arr = img_json.get('set').get('item')
try:
img_url = img_item_arr[0].get('s').get('n')
except:
img_url = img_item_arr.get('s').get('n')
img_url = 'https://images.footaction.com/is/image/%s?wid=600&hei=600&fmt=jpg' % img_url
print(img_url)
global platform
helper.downloadImg(img_url, os.path.join('.', 'imgs', platform, '%s.jpg' % number))
mongo.insert_pending_goods(name, number, url, size_price_arr, ['%s.jpg' % number], platform)
# 上传到七牛
qiniuUploader.upload_2_qiniu(platform, '%s.jpg' % number, './imgs/%s/%s.jpg' % (platform, number))
def start():
crawl_counter = mongo.get_crawl_counter(platform)
# 创建一个队列用来保存进程获取到的数据
q = Queue()
# 有错误的页面链接
error_page_url_queue = Queue()
# 先获取cookie
_, tmpCookie = helper.get('https://www.kickz.com/us/men/shoes/c', myHeaders={
'User-Agent': 'Mozilla/5.0'
}, withCookie=True)
global cookie
cookie['JSESSIONID'] = tmpCookie.get('JSESSIONID', '')
total_page = 20
fetch_page(['https://www.kickz.com/us/men/shoes/c?selectedPage=%d' % page
for page in range(1, total_page + 1)], 1, q, error_page_url_queue, crawl_counter)
total_page = 17
fetch_page(['https://www.kickz.com/us/kids,women/shoes/shoe-sizes/38+,36-2:3,40+,37+,41+,39-1:3,35+,36,36+,39+,39,37,38,41-1:3,42,41,40,39:40,38-2:3,40-2:3,35:36,37:38,37-1:3,41:42/c?selectedPage=%d' % page
for page in range(1, total_page + 1)], 2, q, error_page_url_queue, crawl_counter)
# # 处理出错的链接
# while not error_page_url_queue.empty():
# error_page_url_list = []
# while not error_page_url_queue.empty():
# error_page_url_list.append(error_page_url_queue.get())
# error_page_men_url_list = [url_data.get('url') for url_data in error_page_url_list if url_data.get('gender') == 1]
# fetch_page(error_page_men_url_list, 1, q, error_page_url_queue, crawl_counter)
# error_page_women_url_list = [url_data.get('url') for url_data in error_page_url_list if url_data.get('gender') == 2]
# fetch_page(error_page_women_url_list, 2, q, error_page_url_queue, crawl_counter)
helper.log('done', platform)
def main(chat='A', enabled=False, chat_index=-1):
'''main'''
chat_index = CHAT_ARR.index(chat) if chat_index == -1 else chat_index
b = True
is_enabled = enabled
if chat_index < len(CHAT_ARR):
url = 'https://www.metartx.com/models/all/%s' % CHAT_ARR[chat_index]
pyquery = helper.get(url)
a_arr = pyquery('.list-group-item > a')
for item in a_arr:
if b:
url = item.get('href')
if url == "https://www.metart.com/model/uliya-a/":
is_enabled = True
if is_enabled:
head_img = item.find('img').get('src')
name = item.find('img').get('alt')
json_path = os.path.join('metartx', 'model',
'%s.json' % name)
img_pathh = os.path.join('metartx', 'model',
'%s_MetArtX.jpg' % name)
if not os.path.exists(json_path) or not os.path.exists(
img_pathh):
fetch_model(url, name, head_img)
b = False
else:
b = True
main(chat_index=chat_index + 1, enabled=is_enabled)
def main(chat, enabled=False):
chat_index = CHAT_ARR.index(chat)
'''main'''
b = True
is_enabled = enabled
if chat_index < 26:
url = 'https://www.vivthomas.com/models/all/%s' % CHAT_ARR[chat_index]
pyquery = helper.get(url)
a_arr = pyquery('.list-group-item > a')
for item in a_arr:
if b:
url = item.get('href')
if url == "https://www.metart.com/model/uliya-a/":
is_enabled = True
if is_enabled:
head_img = item.find('img').get('src')
name = item.find('img').get('alt')
json_path = os.path.join(
'vivthomas', 'model', '%s.json' % name)
img_pathh = os.path.join(
'vivthomas', 'model', '%s.jpg' % name)
print(url, name, head_img)
if not os.path.exists(json_path) or not os.path.exists(img_pathh):
fetch_model(url, name, head_img)
b = False
else:
b = True
if chat_index < len(CHAT_ARR) - 1:
main(CHAT_ARR[chat_index + 1], is_enabled)
def main(chat_index=0, enabled=False):
'''main'''
b = True
is_enabled = enabled
if chat_index < 26:
url = 'https://www.eroticbeauty.com/models/all//%s' % CHAT_ARR[
chat_index]
pyquery = helper.get(url)
a_arr = pyquery('.list-group-item > a')
for item in a_arr:
if b:
url = item.get('href')
print('now => %s' % url)
# if url == "https://www.metart.com/model/uliya-a/":
# is_enabled = True
if is_enabled:
head_img = item.find('img').get('src')
name = item.find('img').get('alt')
json_path = os.path.join('eroticbeauty', 'model',
'%s.json' % name)
img_pathh = os.path.join('eroticbeauty', 'model',
'%s.jpg' % name)
if not os.path.exists(json_path) or not os.path.exists(
img_pathh):
fetch_model(url, name, head_img)
b = False
else:
b = True
main(chat_index + 1, is_enabled)
def run(self):
try:
pq = helper.get(self.url, myHeaders=self.headers)
a_list = pq('a.product-image')
for a in a_list:
self.q.put(a.get('href'))
except:
self.error_page_url_queue.put(self.url)
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 run(self):
try:
pq = helper.get(self.url, myHeaders=self.headers)
a_list = pq('div.mainsite_record_listing li > a')
total = len(a_list)
for i in range(0, total):
self.q.put(a_list[i].get('href'))
except:
self.error_page_url_queue.put({'url': self.url, 'gender': self.gender})
def run(self):
# 获取商品详情url
try:
pq = helper.get(self.url, cookies=cookie, myHeaders=self.headers)
for a in pq('a.no-h-over'):
self.q.put(a.get('link'))
# helper.log('[DEBUG] => ' + a.get('link'), platform)
except:
helper.log('[ERROR] => ' + self.url, platform)
self.error_page_url_queue.put({'url': self.url, 'gender': self.gender})
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 run(self):
'''
解析网站源码
'''
time.sleep(random.randint(2, 5))
try:
pq = helper.get(self.url, myHeaders=self.headers, cookies=self.cookies)
# 款型名称
name = pq('h1#pdp_product_title')
if name and len(name) > 0:
name = name[0].text
# 配色的编号
number = pq('li.description-preview__style-color').text().split(':')[1].strip()
# 颜色值
color_value = pq('li.description-preview__color-description').text().split(':')[1].strip()
price = 0
for div in pq('div.text-color-black'):
if div.get('data-test') == 'product-price':
price = float(div.text.replace('$', ''))
break
size_price_arr = []
for input in pq('div.availableSizeContainer input'):
# M 3.5 / W 5
size = input.get('aria-label').replace('W', '').replace('M', '').replace('C', '').strip()
if '/' in size:
size = size.split('/')[0].strip()
size_price_arr.append({
'size': float(size),
'price': price,
'isInStock': input.get('disabled', False) == False
})
img_url = None
for source in pq('noscript > picture > source'):
img_url = source.get('srcset')
break
if img_url:
pass
result = helper.downloadImg(img_url, os.path.join('.', 'imgs', platform, '%s.jpg' % number))
if result == 1:
# 上传到七牛
qiniuUploader.upload_2_qiniu(platform, '%s.jpg' % number, './imgs/%s/%s.jpg' % (platform, number))
mongo.insert_pending_goods(name, number, self.url, size_price_arr, ['%s.jpg' % number], self.gender, color_value, platform, '5be444e3c7e854cab4b252a0', self.crawl_counter, '', True if img_url else False)
else:
helper.log('%s has no name' % self.url, platform)
# name = pq('h1.exp-pdp-title__main-title')
# name = name[0].text
except Exception as e:
global error_detail_url
error_counter = error_detail_url.get(self.url, 1)
error_detail_url[self.url] = error_counter + 1
helper.log('[ERROR] error timer = %s, url = %s' % (error_counter, self.url), platform)
helper.log(e, platform)
if error_counter < 3:
self.q.put(self.url)
def run(self):
try:
pq = helper.get(self.url)
for a in pq('li.item > a'):
self.q.put(a.get('href'))
except:
helper.log('[ERROR] => ' + self.url, platform)
self.error_page_url_queue.put({
'url': self.url,
'gender': self.gender
})
def fetch_page(url, page = 1, total_page = -1):
page_url = '%s?currentPage=%d&sort=name-asc' % (url, page - 1)
pq = helper.get(page_url, cookies, headers)
# 获取商品详情url
a_arr = pq('div.c-product-card > a')
for a in a_arr:
fetch_detail(a.get('href'))
if total_page < 0:
total_str = pq('div.sub strong').text()
total_page = int(math.ceil(int(total_str) / 60))
if page + 1 < total_page:
fetch_page(url, page + 1, total_page)
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 fetchPage(page):
global enalbed
url = '%s/page/%d/' % (BASE_URL, page)
pq = helper.get(url)
for a in pq('h2 > a'):
url = a.get('href')
if not enalbed:
if url == 'http://adultphotosets.ru/metart-andrea-sixth-presenting/':
enalbed = True
if enalbed:
if not fetchGallery(url, page):
return False
return True
def run(self):
# 获取商品详情url
try:
pq = helper.get(self.url, myHeaders=self.headers)
for span in pq('span.product_title'):
a = PyQuery(span).parents('a')
self.q.put(a.attr('href'))
except:
helper.log('[ERROR] => ' + self.url, 'eastbay')
self.error_page_url_queue.put({
'url': self.url,
'gender': self.gender
})
def run(self):
# 获取商品详情url
try:
pq = helper.get(self.url)
for a in pq('div.product_grid_image > a'):
self.q.put('http://www.jimmyjazz.com%s' % a.get('href'))
except:
global platform
helper.log('[ERROR] => ' + self.url, platform)
self.error_page_url_queue.put({
'url': self.url,
'gender': self.gender
})
def fetch_page(url, page=1):
total_page = -1
while True:
page_url = '%s/%d?orderBy=Published' % (url, page)
pq = helper.get(page_url)
if total_page < 0:
span = pq('span.current-page')[0]
total_page = int(span.text.strip().split('(')[1].replace(')', ''))
# 获取商品详情url
for a in pq('li.product > a'):
fetch_detail('https://www.sneakersnstuff.com%s' % a.get('href'),
page)
page += 1
if page > total_page:
# 下一页超过最大页数，break
break
def fetchGallery(url, title, cartoonPage, page=1, urlArr=None):
print('%s => now cartoonPage => %d' % (helper.now(), cartoonPage))
# print('now cartoon => %s' % title)
if not urlArr:
urlArr = []
pq = helper.get('%s/%d' % (url, page))
if not pq:
return False
for img in pq('p>img'):
src = img.get('src')
if src in urlArr:
dirName = os.path.join('cartoon', title)
helper.writeFile('\n'.join(urlArr), u'%s/url.txt' % dirName)
return True
urlArr.append(src)
return fetchGallery(url, title, cartoonPage, page + 1, urlArr)
def run(self):
try:
txt = helper.get(self.url, myHeaders=self.headers, returnText=True)
json_data = json.loads(txt)
item_list = json_data.get('sections')[0].get('items')
for item_data in item_list:
self.q.put(item_data.get('pdpUrl'))
except Exception as e:
error_counter = error_detail_url.get(self.url, 1)
error_detail_url[self.url] = error_counter + 1
helper.log('[ERROR] error timer = %s, url = %s' % (error_counter, self.url), platform)
helper.log(e, platform)
if error_counter < 3:
self.q.put(self.url)
finally:
helper.log('[INFO] %s is done' % self.url, platform)
def run(self):
# 获取商品详情url
try:
html = helper.get(self.url,
myHeaders=self.headers,
returnText=True)
json_data = json.loads(html)
print(json_data.get('products', [])[0])
# for span in pq('span.product_title'):
# a = PyQuery(span).parents('a')
# self.q.put(a.attr('href'))
except:
helper.log('[ERROR] => ' + self.url, platform)
self.error_page_url_queue.put({
'url': self.url,
'gender': self.gender
})
def fetchGallery(url):
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', '0error', title)
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:
# 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>')
return None
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')
# http://t10.imgchili
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:
print('fetchLargeImageUrl failed')
return None
else:
if url != '':
imgUrl.append(url)
i += 1
if len(imgUrl) > 0:
helper.writeFile('\n'.join(imgUrl), '%s/url.txt' % dirName)
return title
def main():
# https://www.eternaldesire.com/models/all/A/
global chatIndex
chatIndex = 12
b = False
while chatIndex < 23:
url = 'https://www.eternaldesire.com/models/all/%s/' % CHAT_ARR[
chatIndex]
pq = helper.get(url)
scoreSpanArr = pq('.update_information_gallery_rating_number')
aArr = pq('.update_information_model_name')
imgArr = pq('td > a> img')
for i in xrange(0, len(imgArr)):
if imgArr[i].get('alt') == 'Mila':
b = True
if b:
fetchModel(aArr[i].get('href'), imgArr[i].get('src'),
imgArr[i].get('alt'), scoreSpanArr[i].text)
# break
chatIndex += 1
def run(self):
'''
解析网站源码
'''
time.sleep(2)
try:
pq = helper.get(self.url, cookie)
name = pq('h1#prodNameId').text()
number = pq('span#supplierArtNumSpan').text()
color_value = pq('span#variantColorId').text()
size_price_arr = []
for a in pq('div#2SizeContainer > div > a'):
arr = [item.strip() for item in a.get('onclick').replace('ProductDetails.changeSizeAffectedLinks(', '').replace(');', '').split('\n')]
# print(arr)
# '8+', => 8+, => 8+
arr[6] = arr[6].replace('\'', '').replace(',', '').replace('Y', '')
size_price_arr.append({
'size': float(arr[6]) if '+' not in arr[6] else float(arr[6].replace('+', '')) + 0.5,
# '115,76 USD', => '115.76 USD'. => '115.76 USD'. => '115.76 => 115.76
'price': float(arr[2].replace(',', '.').replace(' USD\'.', '').replace('\'', '')),
'isInStock': True
})
# print(size_price_arr)
img_downloaded = mongo.is_pending_goods_img_downloaded(self.url)
if not img_downloaded:
img_url = pq('img.productDetailPic').attr('src')
result = helper.downloadImg(img_url, os.path.join('.', 'imgs', platform, '%s.jpg' % number))
if result == 1:
# 上传到七牛
qiniuUploader.upload_2_qiniu(platform, '%s.jpg' % number, './imgs/%s/%s.jpg' % (platform, number))
img_downloaded = True
mongo.insert_pending_goods(name, number, self.url, size_price_arr, ['%s.jpg' % number], self.gender, color_value, platform, '5bc87d6dc7e854cab4875368', self.crawl_counter, img_downloaded=img_downloaded)
except Exception as e:
global error_detail_url
error_counter = error_detail_url.get(self.url, 1)
error_detail_url[self.url] = error_counter + 1
helper.log('[ERROR] error timer = %s, url = %s' % (error_counter, self.url), platform)
helper.log(e, platform)
if error_counter < 3:
self.q.put(self.url)
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_page(url, q, crawl_counter, gender, error_page_url_queue):
total_page = -1
page = 1
page_thread_list = []
while True:
page_url = '%s?ppg=104&page=%d' % (url, page)
# 创建并启动线程
time.sleep(1.2)
page_spider = PageSpider(page_url, q, error_page_url_queue, gender)
page_spider.start()
page_thread_list.append(page_spider)
if total_page < 0:
pq = helper.get(page_url)
div = pq('div.pagination_info')[0]
total_page = int(div.text.strip().split('of ')[1])
page += 1
if page > total_page:
# 下一页超过最大页数，break
break
for t in page_thread_list:
t.join()
goods_thread_list = []
while True:
queue_size = q.qsize()
if queue_size > 0:
# 每次启动5个抓取商品的线程
for i in range(5 if queue_size > 5 else queue_size):
goods_spider = GoodsSpider(q.get(), gender, q, crawl_counter)
goods_spider.start()
goods_thread_list.append(goods_spider)
for t in goods_thread_list:
t.join()
goods_thread_list = []
else:
break
import helper
import constants
# https://api.enterprise.apigee.com/v1/organizations/yemhuynh-eval/environments/prod/caches
for e in constants.ENVS:
caches = []
cacheNames = helper.get("environments/" + e + "/caches")
for name in cacheNames:
cacheInfo = helper.get("environments/" + e + "/caches/" + name)
caches.append(cacheInfo)
helper.dumpConfig("env/" + e + "/caches.json", caches)
#!/usr/bin/env python # -*- coding: utf-8 -*- # # Author: [email protected] # Date: 2017-07-16 15:12:36 import helper import argparse if __name__ == '__main__': # parser = argparse.ArgumentParser() # parser.add_argument("--url", help = "the url of web") # options = parser.parse_args() # http://www.soku.com/search_video/q_王者荣耀_orderby_1_limitdate_0?site=14&page=2 for page in range(1, 99): pq = helper.get( 'http://www.soku.com/search_video/q_王者荣耀_orderby_1_limitdate_0?site=14&page=%d' % page) for a in pq('.v-link > a'): helper.runCmd('you-get -o ./videos --format=mp4 %s' % a.get('href'))
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)))