def goubanjia(self):
"""
:-1: html tag mixed with invalid data
:100:And the most important thing is the port writed in 'class' rather in text.
The website is difficult to spider, but the proxys are very goog
goubanjia proxy http://www.goubanjia.com
"""
version = begin_time()
host = "http://www.goubanjia.com"
html = self.proxy_req(host, 0)
if not html:
return []
trs = html.find_all("tr", class_=["warning", "success"])
for tr in trs:
tds = tr.find_all("td")
ip = tds[2].find_all("a")[0].text + "://"
iplist = tds[0].find_all(["div", "span", not "p"],
class_=not "port")
for index in iplist:
ip += index.text
encode = tds[0].find_all(["div", "span", "p"],
class_="port")[0]["class"][1]
uncode = functools.reduce(
lambda x, y: x * 10 + (ord(y) - ord("A")),
map(lambda x: x, encode), 0)
self.waitjudge.append(ip + ":" + str(int(uncode / 8)))
self.thread_judge()
end_time(version, 2)
def load_collect(self, page):
"""
load collect
"""
version = begin_time()
if not os.path.exists('%scookie_collect' % data_dir):
print('TB cookie not exist!!!')
return
with codecs.open('%scookie_collect' % data_dir, 'r',
encoding='utf-8') as f:
cookie = f.readline()
changeCookie(cookie[:-1])
changeHtmlTimeout(30)
for block in range(page // 10 + 1):
begin = block * 10
end = min(page, (block + 1) * 10)
threadings = []
for index in range(begin, end):
work = threading.Thread(target=self.load_collect_once,
args=(index, ))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
collect = [self.collect[k] for k in sorted(self.collect.keys())]
collect = sum(collect, [])
with codecs.open('%scollect_wyy' % data_dir, 'w',
encoding='utf-8') as f:
f.write("\n".join(collect))
end_time(version)
def get_detail(self):
"""
get summarization from http://news.baidu.com/ns?word=%E6%AF%92%E7%8B%97%E8%82%89&tn=news&from=news&cl=2&rn=20&ct=1
"""
version = begin_time()
threadings = []
with codecs.open('bjh_href_poison.txt', 'r', encoding='utf-8') as f:
href_list = f.readlines()
for index, url in enumerate(href_list):
work = threading.Thread(
target=self.detail_once, args=(index, url,))
threadings.append(work)
for work in threadings:
# time.sleep(.5)
work.start()
for work in threadings:
work.join()
word_list = [self.word_list[k] for k in sorted(self.word_list.keys())]
with codecs.open('bjh_detail_poison', 'w', encoding='utf-8') as f:
f.write("\n".join(word_list))
self.failuredmap = {}
with codecs.open('bjh.log', 'w', encoding='utf-8') as f:
f.write('\n'.join(self.fail))
self.fail = []
end_time(version)
def get_song_detail_thread(self):
"""
get song detail threadings
"""
version = begin_time()
for classify in self.classifylist:
ids = self.get_list_ids(classify)
threadings = []
for oneid in ids:
work = threading.Thread(target=self.get_song_detail,
args=(oneid[1], ))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
self.clean_data()
self.test_song(classify, ids)
self.songlist = []
self.songmap = {}
self.finishlist = []
self.successtime = 0
print(classify + ' Over!')
end_time(version)
def goubanjia(self):
"""
:-1: html tag mixed with invalid data
:100:And the most important thing is the port writed in 'class' rather in text.
The website is difficult to spider, but the proxys are very goog
goubanjia proxy http://www.goubanjia.com
"""
version = begin_time()
host = 'http://www.goubanjia.com'
html = self.proxy_req(host, 0)
if not html:
return []
trs = html.find_all('tr', class_=['warning', 'success'])
for tr in trs:
tds = tr.find_all('td')
ip = tds[2].find_all('a')[0].text + '://'
iplist = tds[0].find_all(['div', 'span', not 'p'],
class_=not 'port')
for index in iplist:
ip += index.text
encode = tds[0].find_all(['div', 'span', 'p'],
class_='port')[0]['class'][1]
uncode = functools.reduce(
lambda x, y: x * 10 + (ord(y) - ord('A')),
map(lambda x: x, encode), 0)
self.waitjudge.append(ip + ':' + str(int(uncode / 8)))
self.threadjude()
end_time(version)
def get_summarization(self):
"""
get summarization from http://news.baidu.com/ns?word=%E6%AF%92%E7%8B%97%E8%82%89&tn=news&from=news&cl=2&rn=20&ct=1
"""
version = begin_time()
threadings = []
for index in range(75):
work = threading.Thread(
target=self.summarization_once, args=(index,))
threadings.append(work)
for work in threadings:
# time.sleep(.5)
work.start()
for work in threadings:
work.join()
# self.text_map = self.total_map[0]
# for index in list(range(1, len(self.total_map))):
# for ids in self.total_map[index]:
# if ids in self.text_map:
# self.text_map[ids] += self.total_map[index][ids]
# else:
# self.text_map[ids] = self.total_map[index][ids]
# print(sum(self.text_map))
word = [self.word[k] for k in sorted(self.word.keys())]
with codecs.open('test', 'w', encoding='utf-8') as f:
f.write("\n".join(word))
end_time(version)
def get_summarization(self):
"""
get summarization from https://www.google.com.hk/search?q=%E6%AF%92%E7%8B%97%E8%82%89&newwindow=1&safe=strict&tbm=nws&ei=FK1KXJ3EJbWx0PEPytmq2AI&start=0&sa=N&ved=0ahUKEwidnv-7p4jgAhW1GDQIHcqsCis4ChDy0wMIRw&biw=1627&bih=427&dpr=2
"""
version = begin_time()
threadings = []
for index in range(25):
work = threading.Thread(
target=self.summarization_once, args=(index,))
threadings.append(work)
for work in threadings:
time.sleep(1)
work.start()
for work in threadings:
work.join()
summarizations = [self.summarizations[k]
for k in sorted(self.summarizations.keys())]
self.summarizations = sum(summarizations, [])
hrefs = [self.hrefs[k] for k in sorted(self.hrefs.keys())]
self.hrefs = sum(hrefs, [])
with codecs.open('google_steal.txt', 'w', encoding='utf-8') as f:
f.write('\n'.join(self.summarizations))
with codecs.open('google_steal_href.txt', 'w', encoding='utf-8') as f:
f.write('\n'.join(self.hrefs))
end_time(version)
def search_goods(self):
version = begin_time()
if not os.path.exists('%swait' % data_dir):
print('wait file not exist!!!')
return
with codecs.open('%swait' % data_dir, 'r', encoding='utf-8') as f:
wait = f.readlines()
threadings = []
for index, goods_name in enumerate(wait):
work = threading.Thread(target=self.search_goods_once,
args=(
goods_name[:-1],
index,
))
threadings.append(work)
for work in threadings:
work.start()
time.sleep(random.randint(5, 9))
for work in threadings:
work.join()
goods_name = [
self.goods_name[k] for k in sorted(self.goods_name.keys())
]
with codecs.open('%swait_goods' % data_dir, 'w',
encoding='utf-8') as f:
f.write('\n'.join(goods_name))
end_time(version)
def load_goods(self):
"""
load goods
"""
version = begin_time()
if not os.path.exists('%scookie' % data_dir):
print('Youdao Note cookie not exist!!!')
return
with codecs.open('%scookie' % data_dir, 'r', encoding='utf-8') as f:
cookie = f.readline()
changeCookie(cookie[:-1])
threadings = []
for index, tid in enumerate(self.request_list):
work = threading.Thread(target=self.load_goods_once,
args=(
index,
tid,
))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
goods = [self.goods[k] for k in sorted(self.goods.keys())]
goods = sum(goods, [])
with codecs.open('%sgoods' % data_dir, 'w', encoding='utf-8') as f:
f.write("\n".join(goods))
end_time(version)
def participles_word(self):
"""
participles word
"""
version = begin_time()
for file in self.filelists:
pkuseg.test(file, file[:-4] + '_pkuseg.txt',
model_name='../Model_retrieval/pkuseg', nthread=20)
end_time(version)
def pre_data_list(self, do_pre):
version = begin_time()
if do_pre == True:
self.load_all(0)
self.load_all(1)
elif do_pre == 2:
self.load_all_pickle(0)
self.load_all_pickle(1)
else:
self.load_basic(1)
end_time(version)
def press_threading(self, url, qps, types):
"""
press url at constant qps
"""
version = begin_time()
threadings = []
for index in range(qps):
work = threading.Thread(
target=self.basic_press, args=(url, 0, types))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
end_time(version)
def have_places(self):
"""
brush class
"""
version = begin_time()
have_places = False
while not have_places:
if self.have_places_once():
send_email('大数据专题', '大数据专题 有名额啦 有名额啦')
send_email('大数据专题', '大数据专题 有名额啦 有名额啦')
send_email('大数据专题', '大数据专题 有名额啦 有名额啦')
have_places = True
time.sleep(random.randint(10, 20))
end_time(version)
def load_index():
''' load index '''
global movie_list
version = begin_time()
text = proxy_req(HOMEPAGE_URL, 3)
if not len(text):
if can_retry(HOMEPAGE_URL):
load_index()
return
movie_list = re.findall('《(.*?)》', text)
movie_more = re.findall('href="(.*?)">更多', text)
for uri in movie_more:
load_other(uri)
threading_list = [threading.Thread(
target=load_other, args=(ii,)) for ii in movie_another]
shuffle_batch_run_thread(threading_list, 100)
threading_list = [threading.Thread(
target=load_other, args=(ii,)) for ii in movie_again]
shuffle_batch_run_thread(threading_list, 100)
# 对电影列表去重
movie_list = set(movie_list)
# 导出爬取的 电影列表
out_path = 'dytt8_result.txt'
with open(out_path, 'w') as f:
f.write('\n'.join(movie_list))
url_num = len([*movie_more, *movie_another]) + 1
movie_num = len(movie_list)
echo(1, 'Requests num: {}\nMovie num: {}\nOutput path: {}\nSpend time: {:.2f}s\n'.format(
url_num, movie_num, out_path, end_time(version, 0)))
def kuaidaili(self, page: int):
"""
kuaidaili https://www.kuaidaili.com/free/
"""
version = begin_time()
threadings = []
for index in range(1, page + 1):
work = threading.Thread(target=self.kuaidailithread, args=(index,))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
self.thread_judge()
end_time(version, 2)
def test_db(self, types: int):
""" test proxy in db can use """
version = begin_time()
typestr = ""
if types == 2:
typestr = "(0,1,2,3)"
elif types == 1:
typestr = "(1,3)"
else:
typestr = "(0,2)"
results = self.Db.select_db(self.select_all % typestr)
if results:
for index in results:
self.waitjudge.append(index[0])
self.thread_judge()
self.init_proxy()
end_time(version, 2)
def sixsixip(self, area: int, page: int):
"""
66ip proxy http://www.66ip.cn/areaindex_{area}/{page}.html
"""
version = begin_time()
threadings = []
for index in range(1, area + 1):
for pageindex in range(1, page + 1):
echo("2|debug", "{} {}".format(index, pageindex))
work = threading.Thread(target=self.sixsixthread,
args=(index, pageindex))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
self.thread_judge()
end_time(version, 2)
def sixsixip(self, area, page):
"""
66ip proxy http://www.66ip.cn/areaindex_{area}/{page}.html
"""
version = begin_time()
threadings = []
for index in range(1, area + 1):
for pageindex in range(1, page + 1):
echo(2, str(index) + ' ' + str(pageindex))
work = threading.Thread(target=self.sixsixthread,
args=(index, pageindex))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
self.threadjude()
end_time(version)
def get_movie_lists(self):
''' get movie list '''
version = begin_time()
movie_get = []
for kk in range(0, 1100, 100):
for jj in self.sort_list:
for ii in self.tag_movie:
movie_get.append(threading.Thread(
target=self.get_movie_lists_once, args=('movie', ii, jj, kk,)))
for ii in self.tag_tv:
movie_get.append(threading.Thread(
target=self.get_movie_lists_once, args=('tv', ii, jj, kk,)))
shuffle_batch_run_thread(movie_get, 500, True)
again_list = [threading.Thread(target=self.get_movie_lists_once, args=(
ii[0], ii[1], ii[2], ii[3],)) for ii in self.again_list]
shuffle_batch_run_thread(again_list, 500, True)
self.again_list = []
echo(1, len(self.movie_id2name.keys()))
changeHtmlTimeout(40)
movie_get = []
tag_categories = self.tag_categories
for mm in range(0, 10000, 1000):
for tags in tag_categories[0][1:]:
for genres in tag_categories[1][1:]:
for ii, jj in self.yearMap.values():
year_range = '{},{}'.format(ii, jj)
for sorts in self.tabs:
movie_get.append(threading.Thread(
target=self.get_movie_list_from_tabs, args=(sorts, tags, genres, year_range, mm,)))
echo(2, 'Thread Num:', len(movie_get))
shuffle_batch_run_thread(movie_get, 900, True)
again_list = [threading.Thread(target=self.get_movie_list_from_tabs, args=(
ii[0], ii[1], ii[2], ii[3], ii[4],)) if len(ii) == 5 else threading.Thread(target=self.get_movie_lists_once, args=(
ii[0], ii[1], ii[2], ii[3],)) for ii in self.again_list]
shuffle_batch_run_thread(again_list, 900, True)
time.sleep(120)
changeJsonTimeout(10)
for ii in self.rank_list:
self.get_movie_rank(ii, 0)
if ii == 'top250':
self.get_movie_rank(ii, 100)
self.get_movie_rank(ii, 200)
movie_list = self.movie_id2name.keys()
output_path = '{}douban_movie_id'.format(data_dir)
with open(output_path + '.txt', 'w') as f:
f.write('\n'.join([str(ii) for ii in movie_list]))
dump_bigger(self.movie_id2name, output_path + '.pkl')
movie_num = len(movie_list)
echo(1, 'Movie num: {}\nOutput path: {}\nSpend time: {:.2f}s\n'.format(
movie_num, output_path, end_time(version, 0)))
def data5u(self):
"""
data5u proxy http://www.data5u.com/
no one can use
"""
version = begin_time()
url_list = ["", "free/gngn/index.shtml", "free/gwgn/index.shtml"]
host = "http://www.data5u.com/"
for uri in url_list:
html = self.proxy_req(host + uri, 0)
if not html:
continue
table = html.find_all("ul", class_="l2")
for index in table:
tds = index.find_all("li")
ip = tds[3].text
self.waitjudge.append("{}://{}:{}".format(ip, tds[1].text, tds[2].text))
self.thread_judge()
end_time(version, 2)
def xici_proxy(self, page: int):
"""
xici proxy http://www.xicidaili.com/nn/{page}
The first proxy I use, but now it can not use it mostly.
"""
if not str(page).isdigit():
echo("0|warning", "Please input num!")
return []
version = begin_time()
url = "http://www.xicidaili.com/nn/%d"
for index in range(1, page + 1):
html = basic_req(url % index, 0)
tem = html.find_all("tr")
for index in range(1, len(tem)):
tds = tem[index].find_all("td")
ip = tds[5].text.lower()
self.waitjudge.append("{}://{}:{}".format(ip, tds[1].text, tds[2].text))
self.thread_judge()
end_time(version, 2)
def data5u(self):
"""
data5u proxy http://www.data5u.com/
no one can use
"""
version = begin_time()
url_list = ['', 'free/gngn/index.shtml', 'free/gwgn/index.shtml']
host = 'http://www.data5u.com/'
for uri in url_list:
html = self.proxy_req(host + uri, 0)
if not html:
continue
table = html.find_all('ul', class_='l2')
for index in table:
tds = index.find_all('li')
ip = tds[3].text
self.waitjudge.append(ip + '://' + tds[0].text + ':' +
tds[1].text)
self.threadjude()
end_time(version)
def xiciproxy(self, page):
"""
xici proxy http://www.xicidaili.com/nn/{page}
The first proxy I use, but now it can not use it mostly.
"""
if not str(page).isdigit():
echo(0, "Please input num!")
return []
version = begin_time()
url = 'http://www.xicidaili.com/nn/%d'
for index in range(1, page + 1):
html = basic_req(url % (index), 0)
tem = html.find_all('tr')
for index in range(1, len(tem)):
tds = tem[index].find_all('td')
ip = tds[5].text.lower()
self.waitjudge.append(ip + '://' + tds[1].text + ':' +
tds[2].text)
self.threadjude()
end_time(version)
def get_href(self):
"""
get summarization from http://news.baidu.com/ns?word=%E6%AF%92%E7%8B%97%E8%82%89&tn=news&from=news&cl=2&rn=20&ct=1
"""
version = begin_time()
threadings = []
for index in range(71):
work = threading.Thread(
target=self.href_once, args=(index,))
threadings.append(work)
for work in threadings:
# time.sleep(.5)
work.start()
for work in threadings:
work.join()
href_map = [self.href_map[k] for k in sorted(self.href_map.keys())]
self.href_map = sum(href_map, [])
with codecs.open('bjh_href_poison.txt', 'w', encoding='utf-8') as f:
f.write("\n".join(self.href_map))
end_time(version)
def testdb(self, types):
'''
test proxy in db can use
'''
version = begin_time()
typestr = ''
if types == 2:
typestr = '(0,1,2,3)'
elif types == 1:
typestr = '(1,3)'
else:
typestr = '(0,2)'
results = self.Db.select_db(self.select_all % typestr)
if results != 0:
for index in results:
self.waitjudge.append(index[0])
self.threadjude()
else:
pass
self.initproxy()
end_time(version)
def build_md(self, load_img=False):
"""
build md
"""
version = begin_time()
threadings = []
for index, tid in enumerate(self.request_list):
work = threading.Thread(target=self.build_md_once,
args=(
index,
tid,
))
threadings.append(work)
for work in threadings:
work.start()
for work in threadings:
work.join()
if not load_img:
return
img_map = {k: self.img_map[k] for k in sorted(self.img_map.keys())}
img_threadings = []
for index in img_map.keys():
for img_id, img_url in enumerate(img_map[index]):
work = threading.Thread(target=self.load_img,
args=(
index,
img_id,
img_url,
))
img_threadings.append(work)
for work in img_threadings:
work.start()
for work in img_threadings:
work.join()
end_time(version)
def load_proxies_test(self):
""" load mode & test proxies """
version = begin_time()
self.load_proxies_list()
proxies_len = len(self.waitjudge)
self.thread_judge()
canuse_len = len(self.canuse_proxies)
echo(
"1|info",
"\nTotal Proxies num: {}\nCan use num: {}\nTime spend: {}\n".
format(proxies_len, canuse_len, end_time(version)),
)
with open("{}canuse_proxies.txt".format(data_dir), "w") as f:
f.write("\n".join(self.canuse_proxies))
def get_classify(self):
"""
get classify from /discover/playlist
"""
version = begin_time()
self.classifylist = {}
host = 'https://music.163.com/discover/playlist'
html = proxy_req(host, 0)
if not html:
print('Empty')
if can_retry(host):
self.get_classify()
return []
alist = html.find_all('a', class_='s-fc1')
if not len(alist):
if can_retry(host):
self.get_classify()
print(html)
for index in alist:
self.classifylist[index.text] = index['href']
end_time(version)
def get_summarization(self):
"""
get summarization from http://news.baidu.com/ns?word=%E6%AF%92%E7%8B%97%E8%82%89&tn=news&from=news&cl=2&rn=20&ct=1
"""
version = begin_time()
threadings = []
for index in range(30):
work = threading.Thread(
target=self.summarization_once, args=(index,))
threadings.append(work)
for work in threadings:
# time.sleep(.5)
work.start()
for work in threadings:
work.join()
summarizations = [self.summarizations[k]
for k in sorted(self.summarizations.keys())]
self.summarizations = sum(summarizations, [])
with codecs.open('news_posion.txt', 'w', encoding='utf-8') as f:
f.write('\n'.join(self.summarizations))
end_time(version)
def get_movie_lists(self):
''' get movie list '''
version = begin_time()
movie_get = []
for ii in self.tag:
for jj in self.sort_list:
movie_get.append(threading.Thread(
target=self.get_movie_lists_once, args=('movie', ii, jj, 0,)))
for ww in movie_get:
ww.start()
for ww in movie_get:
ww.join()
movie_list = set(sum(self.movie_id_dict.values(), []))
output_path = '{}douban_movie_id.txt'.format(data_dir)
with open(output_path, 'w') as f:
f.write('\n'.join([str(ii) for ii in movie_list]))
movie_num = len(movie_list)
echo(1, 'Movie num: {}\nOutput path: {}\nSpend time: {:.2f}s\n'.format(
movie_num, output_path, end_time(version, 0)))