def parse_step_1(self, response):
if response.status == 200 or response.status == 301:
if response.url == 'http://www.59pic.com/waf_verify.htm':
return
max_num = response.css("#pageNum a.a1::text").extract_first(
default="1").lstrip(u'共').rstrip(u'张')
type = u'美女大全'
title = response.css("title::text").extract_first().split('-')[0]
img_path = response.css("#bigImg::attr(src)").extract_first(
default='')
bulk_sqls = []
bulk_sqls.append(
"('%s', '%s', '%s', '%s', '%s', 0)" %
(self._source, type, title, response.url, img_path))
try:
for num in range(2, int(max_num) + 1):
page_url = response.url.rstrip('.html') + '_' + str(
num) + '.html'
bulk_sqls.append("('%s', '%s', '%s', '%s', '', 0)" %
(self._source, type, title, page_url))
except:
print '解释失败'
_execute(
"insert into mzitu_all(source, type, title, page_url, img_path, state) values"
+ ",".join(bulk_sqls))
pass
def parse_step_1(self, response):
if response.status == 200 or response.status == 301:
max_num = response.css(
"#page > a:nth-last-child(3)::text").extract_first(default="1")
type = u'妹子图'
title = response.css(".main > .article > h2::text").extract_first(
default='NAN')
img_path = response.css(
"#content > a > img::attr(src)").extract_first(default='')
bulk_sqls = []
bulk_sqls.append(
"('%s', '%s', '%s', '%s', '%s', 0)" %
(self._source, type, title, response.url, img_path))
try:
for num in range(2, int(max_num) + 1):
page_url = response.url + '/' + str(num)
bulk_sqls.append("('%s', '%s', '%s', '%s', '', 0)" %
(self._source, type, title, page_url))
except:
print '解释失败'
_execute(
"insert into mzitu_all(source, type, title, page_url, img_path, state) values"
+ ",".join(bulk_sqls))
pass
def parse_item(self, response):
params = response.url.split('/')
if params[-3] == 'fuli' and params[-1] == '':
return
type = response.css('#xiaohua_list .left .bt .l > a:nth-child(3)::text'
).extract_first(default='NAN')
title = response.css("#xiaohua_list .left .cont > h1::text"
).extract_first(default='NAN')
if title != 'NAN':
try:
title = title[0:title.rfind('(') - 1]
except:
pass
img_path = response.css("#xiaohua_list .left .content img::attr(src)"
).extract_first(default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_all(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_step_2(self, response):
if response.status == 200 or response.status == 301:
img_path = response.css("#bigImg::attr(src)").extract_first(
default='')
if "" != img_path:
_execute(
"update mzitu_all set img_path = '%s' where page_url = '%s'"
% (img_path, response.url))
pass
def parse_item(self, response):
type = response.css('.warp .articleV4Info > a::text').extract_first(default=u'美女图片')
title = response.css("#picBody img::attr(alt)").extract_first(default='NAN')
img_path = response.css("#picBody img::attr(src)").extract_first(default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_youzi(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
if response.url.find('list_11') != -1:
return
type = u'美女图片'
title = response.css(
"#picBody > p > a > img::attr(alt)").extract_first(default='NAN')
img_path = response.css(
"#picBody > p > a > img::attr(src)").extract_first(default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_all(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
if response.url.find('index_') != -1:
return
type = u'妹子图'
title = response.css(".indexbox .r .tcontent img::attr(alt)"
).extract_first(default='NAN')
img_path = response.css(
".indexbox .r .tcontent img::attr(src)").extract_first(default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_all(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
if response.url.find('list_9') != -1:
return
type = response.css('.photo .topmbx > a:nth-child(3)::text'
).extract_first(default=u'美女图片')
title = response.css("#big-pic img::attr(alt)").extract_first(
default='NAN')
img_path = response.css("#big-pic img::attr(src)").extract_first(
default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_all(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
if response.url.find('list_') != -1:
return
params = response.url.split('.')
if params[-1] != 'html':
return
type = response.css('.warp.mar .warp.oh .articleV4Info > a::text').extract_first(default=u'妹子图')
title = response.css("#picBody img::attr(alt)").extract_first(default='NAN')
img_path = response.css("#picBody img::attr(src)").extract_first(default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_all(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
type = response.css('.place > a:nth-child(2)::text').extract_first(
default='MM131ÃÀŮͼƬ')
title = response.css(".content .content-pic img::attr(alt)"
).extract_first(default='NAN')
img_path = response.css(
".content .content-pic img::attr(src)").extract_first(default='')
try:
title = title[0:title.rindex(u'(')]
except:
title = title
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_mm131(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
params = response.url.split('/')
if params[-2] == 'archives':
type = response.css('section > .content-wrap span.item-3 > a::text'
).extract_first(default='NAN')
title = response.css(
"section > .content-wrap header.article-header > h1.article-title::text"
).extract_first(default='NAN')
bulk_sqls = []
for img_path in response.css(
'section > .content-wrap article.article-content img::attr(src)'
).extract():
bulk_sqls.append(
"('%s', '%s', '%s', '%s', '%s', 0)" %
(self._source, type, title, response.url, img_path))
_execute(
"insert into mzitu_all(source, type, title, page_url, img_path, state) values"
+ ",".join(bulk_sqls))
pass
def parse_item(self, response):
type = response.css(
'.photo .tsmaincont-desc > span:nth-child(3) > a::text'
).extract_first(default=u'美女图片')
title = response.css("#big-pic img::attr(alt)").extract_first(
default='NAN')
img_path = response.css("#big-pic img::attr(src)").extract_first(
default='')
if 'NAN' == title and img_path == '':
return
try:
title = re.sub(r'第\d+张', '', title)
except:
title = title
sql = "insert into mzitu_aitaotu(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def parse_item(self, response):
if response.url.find('list') == -1:
return
type = u'搂妹子'
title = response.css("title::text").extract_first(default='NAN')
try:
if title[-1] == ')':
r = title.rindex('(')
title = title[0:r]
except:
pass
img_path = response.css("#content > img::attr(src)").extract_first(
default='')
if 'NAN' == title and img_path == '':
return
sql = "insert into mzitu_all(source, type, title, page_url, img_path, state) values('%s', '%s', '%s', '%s', '%s', 0)" % \
(self._source, type, title, response.url, img_path)
_execute(sql)
pass
def item_completed(self, results, item, info):
ok_paths = []
err_paths = []
for i in range(0, len(results)):
if results[i][0]:
ok_paths.append(item['image_paths'][i])
else:
err_paths.append(item['image_paths'][i])
# image_paths = [x['path'] for ok, x in results if ok]
# download_image_paths = [x['url'] for ok, x in results if ok]
# if not image_paths:
# raise DropItem("Item contains no images")
if item['source'] == 'mm29':
if len(ok_paths) > 0:
_ok_paths = []
for path in ok_paths:
_ok_paths.append(path + '/800.jpg')
_execute(
"update mzitu_aitaotu_n set state = 1 where img_path in ('%s')"
% ("','".join(_ok_paths)))
if len(err_paths):
_err_paths = []
for path in err_paths:
_err_paths.append(path + '/800.jpg')
_execute(
"update mzitu_aitaotu_n set state = 9 where img_path in ('%s')"
% ("','".join(_err_paths)))
else:
if len(ok_paths) > 0:
_execute(
"update mzitu_aitaotu_n set state = 1 where img_path in ('%s')"
% ("','".join(ok_paths)))
if len(err_paths) > 0:
_execute(
"update mzitu_aitaotu_n set state = 9 where img_path in ('%s')"
% ("','".join(err_paths)))
return item
