def get_conferences():
files = util.listdir(CONFERENCE_FOLDER)
util.mkdir(CONFERENCE_CRALWED_FOLDER)
cnt = 0
conf = util.load_json('conf_name.json')
for file_name in files:
save_path = os.path.join(CONFERENCE_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name))
if data['short'] not in conf.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = conf[data['short']]
data['sub'] = {}
for sub in subs:
if sub not in conf.keys():
continue
html = util.get_page('http://dblp.uni-trier.de/db/conf/' + sub)
data['sub'][sub] = {}
data['sub'][sub]['pub'] = get_publications(html)
data['sub'][sub]['name'] = conf[sub]
cnt += 1
print cnt, len(files), data['short']
util.save_json(save_path, data)
def get_links(prefix, html):
journals = util.find_journals(html)
conferences = util.find_conferences(html)
journals = list(set(journals))
conferences = list(set(conferences))
#authors = util.find_authors(html)
links = []
for j in journals:
if j[0].startswith(prefix):
print '\t', j[0]
inner_url = 'http://dblp.uni-trier.de/db/journals/' + j[0]
inner = util.get_page(inner_url)
#links += get_links('###', inner)
else:
links.append(('journal', j[0].split('/')[0].split('#')[0]))
for c in conferences:
if c[0].startswith(prefix):
print '\t', c[0]
inner_url = 'http://dblp.uni-trier.de/db/conf/' + c[0]
inner = util.get_page(inner_url)
#links += get_links('###', inner)
else:
links.append(('conference', c[0].split('/')[0].split('#')[0]))
#for a in authors:
#links.append(('author', a[0].split('#')[0]))
pass
links = list(set(links))
return links
def get_links(prefix, html):
journals = util.find_journals(html)
conferences = util.find_conferences(html)
journals = list(set(journals))
conferences = list(set(conferences))
#authors = util.find_authors(html)
links = []
for j in journals:
if j[0].startswith(prefix):
print '\t', j[0]
inner_url = 'http://dblp.uni-trier.de/db/journals/' + j[0]
inner = util.get_page(inner_url)
#links += get_links('###', inner)
else:
links.append(('journal', j[0].split('/')[0].split('#')[0]))
for c in conferences:
if c[0].startswith(prefix):
print '\t', c[0]
inner_url = 'http://dblp.uni-trier.de/db/conf/' + c[0]
inner = util.get_page(inner_url)
#links += get_links('###', inner)
else:
links.append(('conference', c[0].split('/')[0].split('#')[0]))
#for a in authors:
#links.append(('author', a[0].split('#')[0]))
pass
links = list(set(links))
return links
def get_conferences():
files = util.listdir(CONFERENCE_FOLDER)
util.mkdir(CONFERENCE_CRALWED_FOLDER)
cnt = 0
conf = util.load_json('conf_name.json')
for file_name in files:
save_path = os.path.join(CONFERENCE_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name))
if data['short'] not in conf.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = conf[data['short']]
data['sub'] = {}
for sub in subs:
if sub not in conf.keys():
continue
html = util.get_page('http://dblp.uni-trier.de/db/conf/' + sub)
data['sub'][sub] = {}
data['sub'][sub]['pub'] = get_publications(html)
data['sub'][sub]['name'] = conf[sub]
cnt += 1
print cnt, len(files), data['short']
util.save_json(save_path, data)
def get_user_info(u,fp):
ourl = "http://www.toutiao.com/c/user/%s/" % u
url,html = util.get_page({"url":ourl})
p,h = get_urlinfo(url)
params = get_params("func.js")
uid = get_userinfo(html)
if params is not None and uid is not None:
params = json.loads(params)
params["user_id"] = uid
path = "/c/user/article/"
nurl = "%s//%s%s" % (p,h,path)
count = 3
while True:
url,html = util.get_page({"url":nurl,"data":params,"method":"post"})
if html is None or len(html) == 0:
util.log_msg("could not get data from url:%s,data:%s,uid:%s" % (nurl,str(params),u))
break
mp = json.loads(html)
if "data" in mp and isinstance(mp["data"],list):
if len(mp["data"]) == 0:
util.log_msg("no data from response.url:%s" % nurl)
result = []
for item in mp["data"]:
turl = util.parse_url(url,item["source_url"])
try:
get_article(turl,url,item,fp,result)
except Exception:
tp, e,trace = sys.exc_info()
util.log_msg("get article(url:%s) info error:%s" % (turl,str(e)))
if len(result) > 0:
if fp is None:
insert_into_db(result)
else:
for item in result:
fp.write("[%s]\t%s\t%s\n" % (time.ctime(),u,json.dumps(item)))
else:
util.log_msg("no data in content.url:%s" % nurl)
if mp["has_more"]:
params = get_params("func.js")
params = json.loads(params)
params["user_id"] = uid
nxt = mp["next"]
for key in nxt.keys():
params[key]=nxt[key]
else:
break
count -= 1
if count <= 0:
break
else:
util.log_msg("could not parse data from html file,need to check this out.url:%s,referer:%s." % (ourl,referer))
def get_journals():
pos, cnt = 1, 0
util.mkdir(JOURNAL_FOLDER)
while True:
html = util.get_page(JOURNAL_URL + str(pos))
links = util.find_journals(html)
once_cnt = 0
for link in links:
if link[0] == '' or '?' in link[0]:
continue
data = {}
data['type'] = 'journal'
data['short'] = link[0]
data['name'] = link[1]
data['url'] = 'http://dblp.uni-trier.de/db/journals/' + data[
'short']
util.save_json(
os.path.join(JOURNAL_FOLDER, util.hex_hash(data['short'])),
data)
cnt += 1
once_cnt += 1
if once_cnt == 0:
break
pos += 100
print 'Journal', cnt
def crawl_data5u(self):
start_url = 'http://www.data5u.com/free/gngn/index.shtml'
headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding':
'gzip, deflate',
'Accept-Language':
'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Cache-Control':
'max-age=0',
'Connection':
'keep-alive',
'Cookie':
'JSESSIONID=47AA0C887112A2D83EE040405F837A86',
'Host':
'www.data5u.com',
'Referer':
'http://www.data5u.com/free/index.shtml',
'Upgrade-Insecure-Requests':
'1',
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36',
}
html = get_page(start_url, options=headers)
if html:
ip_address = re.compile(
'<span><li>(\d+\.\d+\.\d+\.\d+)</li>.*?<li class=\"port.*?>(\d+)</li>',
re.S)
re_ip_address = ip_address.findall(html)
for address, port in re_ip_address:
result = address + ':' + port
yield result.replace(' ', '')
def main(forum_post_number,
version,
api_url='https://wiki.factorio.com/api.php',
version_nav=True):
session = requests.Session()
edit_token = get_edit_token(session, api_url)
latest_version_page_name = 'Main_Page/Latest_versions'
version_nav_page_name = 'Template:VersionNav'
latest_version_page = get_page(session, api_url, latest_version_page_name)
if version_nav:
version_nav_page = get_page(session, api_url, version_nav_page_name)
if version in latest_version_page:
return f'Version {version} already found on "{latest_version_page_name}". Aborting.'
if version_nav:
if version in version_nav_page:
return f'Version {version} already found on "{version_nav_page_name}". Aborting.'
if 'None' not in latest_version_page:
new_latest_version_page = re.sub(
r'({{Translation\|Latest experimental version}}: \[https:\/\/forums\.factorio\.com\/)\d+ \d\.\d+\.\d+',
rf'\g<1>{forum_post_number} {version}', latest_version_page)
else:
new_latest_version_page = re.sub(
r'({{Translation\|Latest experimental version}}: ){{Translation\|None}}',
rf'\g<1>[https://forums.factorio.com/{forum_post_number} {version}]',
latest_version_page)
if version_nav:
new_version_nav_page = re.sub(
r'(}}\n)(}}\n<noinclude>{{Documentation}}<\/noinclude>)',
rf'\1* {{{{TransLink|Version history/{version[:version.rfind(".")+1]}0#{version}|{version}}}}}\n\2',
version_nav_page)
edit_response_latest_version_page = edit_page(session, api_url, edit_token,
latest_version_page_name,
new_latest_version_page,
f'{version}')
if version_nav:
edit_response_version_nav_page = edit_page(session, api_url,
edit_token,
version_nav_page_name,
new_version_nav_page,
f'{version}')
return edit_response_latest_version_page.text + (
('\n' + edit_response_version_nav_page.text) if version_nav else '')
def crawl_89ip(self):
start_url = 'http://www.89ip.cn/tqdl.html?num=50&address=&kill_address=&port=&kill_port=&isp='
html = get_page(start_url)
if html:
find_ips = re.compile('(\d+\.\d+\.\d+\.\d+:\d+)', re.S)
ip_ports = find_ips.findall(html)
for address_port in ip_ports:
yield address_port
def crawl_kxdaili(self):
for i in range(1, 4):
start_url = 'http://www.kxdaili.com/ipList/{}.html#ip'.format(i)
html = get_page(start_url)
ip_adress = re.compile('<tr.*?>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
re_ip_adress = ip_adress.findall(html)
for adress, port in re_ip_adress:
result = adress + ':' + port
yield result.replace(' ', '')
def crawl_ip181(self):
start_url = 'http://www.ip181.com/'
html = get_page(start_url)
ip_adress = re.compile('<tr.*?>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
# \s* 匹配空格
re_ip_adress = ip_adress.findall(html)
for adress, port in re_ip_adress:
result = adress + ':' + port
yield result.replace(' ', '')
def get_journals():
files = util.listdir(JOURNAL_FOLDER)
cnt = 0
jour = {}
for file_name in files:
data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name))
html = util.get_page(data['url'])
full_name = get_full_name(html)
cnt += 1
print cnt, len(files), data['short'], '|', full_name
if '404' not in full_name:
jour[data['short']] = full_name
subs = get_subs(data['short'], html)
for sub in subs:
html = util.get_page('http://dblp.uni-trier.de/db/journals/' +
sub)
jour[sub] = get_full_name(html)
print '\t', sub, jour[sub]
util.save_json('jour_name.json', jour)
def crawl_premproxy(self):
for i in ['China-01', 'China-02', 'China-03', 'China-04', 'Taiwan-01']:
start_url = 'https://premproxy.com/proxy-by-country/{}.htm'.format(
i)
html = get_page(start_url)
if html:
ip_adress = re.compile('<td data-label="IP:port ">(.*?)</td>')
re_ip_adress = ip_adress.findall(html)
for adress_port in re_ip_adress:
yield adress_port.replace(' ', '')
def __init__(self, shelf_id, username='', password=''):
self.shelf = shelf_id
self.usr = username
self.pas = password
self.first_page = bs4.BeautifulSoup(get_page(self.shelf, 1, LIST_VIEW), 'lxml')
self.story_count = None
self.pages = None
self.stories = None
self.perchap_wc = None
self.wordcount = None
def crawl_kuaidaili(self):
for page in range(1, 4):
start_url = 'https://www.kuaidaili.com/free/inha/{}/'.format(page)
html = get_page(start_url)
ip_adress = re.compile(
'<td data-title="IP">(.*)</td>\s*<td data-title="PORT">(\w+)</td>'
)
re_ip_adress = ip_adress.findall(html)
for adress, port in re_ip_adress:
result = adress + ':' + port
yield result.replace(' ', '')
def crawl_xicidaili(self):
for page in range(1, 4):
start_url = 'http://www.xicidaili.com/wt/{}'.format(page)
html = get_page(start_url)
ip_adress = re.compile(
'<td class="country"><img src="http://fs.xicidaili.com/images/flag/cn.png" alt="Cn" /></td>\s*<td>(.*?)</td>\s*<td>(.*?)</td>'
)
re_ip_adress = ip_adress.findall(html)
for adress, port in re_ip_adress:
result = adress + ':' + port
yield result.replace(' ', '')
def crawl_ip3366(self):
for page in range(1, 4):
start_url = 'http://www.ip3366.net/free/?stype=1&page={}'.format(
page)
html = get_page(start_url)
ip_address = re.compile('<tr>\s*<td>(.*?)</td>\s*<td>(.*?)</td>')
# \s * 匹配空格，起到换行作用
re_ip_address = ip_address.findall(html)
for address, port in re_ip_address:
result = address + ':' + port
yield result.replace(' ', '')
def crawl_data5u(self):
for i in ['gngn', 'gnpt']:
start_url = 'http://www.data5u.com/free/{}/index.shtml'.format(i)
html = get_page(start_url)
ip_adress = re.compile(
' <ul class="l2">\s*<span><li>(.*?)</li></span>\s*<span style="width: 100px;"><li class=".*">(.*?)</li></span>'
)
re_ip_adress = ip_adress.findall(html)
for adress, port in re_ip_adress:
result = adress + ':' + port
yield result.replace(' ', '')
def get_conferences():
files = util.listdir(CONFERENCE_FOLDER)
cnt = 0
conf = {}
for file_name in files:
data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name))
html = util.get_page(data['url'])
full_name = get_full_name(html)
cnt += 1
try:
print cnt, len(files), data['short'], '|', full_name
if '404' not in full_name:
conf[data['short']] = full_name
subs = get_subs(data['short'], html)
for sub in subs:
html = util.get_page('http://dblp.uni-trier.de/db/conf/' +
sub)
conf[sub] = get_full_name(html)
print '\t', sub, conf[sub]
except:
pass
util.save_json('conf_name.json', conf)
def crawl_daili66(self, page_count=4):
start_url = 'http://www.66ip.cn/{}.html'
urls = [start_url.format(page) for page in range(1, page_count + 1)]
for url in urls:
print('Crawling', url)
html = get_page(url)
if html:
doc = pq(html)
trs = doc('.containerbox table tr:gt(0)').items()
for tr in trs:
ip = tr.find('td:nth-child(1)').text()
port = tr.find('td:nth-child(2)').text()
yield ':'.join([ip, port])
def get_journals():
files = util.listdir(JOURNAL_FOLDER)
util.mkdir(JOURNAL_CRALWED_FOLDER)
cnt = 0
for file_name in files:
save_path = os.path.join(JOURNAL_CRALWED_FOLDER, file_name)
data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name))
html = util.get_page(data['url'])
full_name = get_full_name(html)
data['name'] = full_name
cnt += 1
print cnt, len(files), data['short']
data['links'] = get_links(data['short'], html)
def get_journals(): files = util.listdir(JOURNAL_FOLDER) util.mkdir(JOURNAL_CRALWED_FOLDER) cnt = 0 for file_name in files: save_path = os.path.join(JOURNAL_CRALWED_FOLDER, file_name) data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name)) html = util.get_page(data['url']) full_name = get_full_name(html) data['name'] = full_name cnt += 1 print cnt, len(files), data['short'] data['links'] = get_links(data['short'], html)
def get_authors():
files = util.listdir(AUTHOR_FOLDER)
util.mkdir(AUTHOR_CRALWED_FOLDER)
for file_name in files:
save_path = os.path.join(AUTHOR_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(AUTHOR_FOLDER, file_name))
html = util.get_page(data['url'])
full_name = get_full_name(html)
data['name'] = full_name
print data['short'], full_name
data['links'] = get_links(data['short'], html)
util.save_json(save_path, data)
def crawl_daili66(self, count=20):
"""
获取代理66
:param count:
:return:
"""
url = 'http://www.66ip.cn/mo.php?tqsl={}'.format(count)
print('Crawling 66', url)
html = get_page(url)
if html:
ret = re.findall(r'\d+\.\d+\.\d+\.\d+:\d+', html)
for ip in ret:
yield ip
def get_authors(): files = util.listdir(AUTHOR_FOLDER) util.mkdir(AUTHOR_CRALWED_FOLDER) for file_name in files: save_path = os.path.join(AUTHOR_CRALWED_FOLDER, file_name) if util.exists(save_path): continue data = util.load_json(os.path.join(AUTHOR_FOLDER, file_name)) html = util.get_page(data['url']) full_name = get_full_name(html) data['name'] = full_name print data['short'], full_name data['links'] = get_links(data['short'], html) util.save_json(save_path, data)
def get_journals():
files = util.listdir(JOURNAL_FOLDER)
util.mkdir(JOURNAL_CRALWED_FOLDER)
cnt = 0
jour = util.load_json('jour_name.json')
for file_name in files:
save_path = os.path.join(JOURNAL_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name))
if data['short'] not in jour.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = jour[data['short']]
data['sub'] = {}
for sub in subs:
html = util.get_page('http://dblp.uni-trier.de/db/journals/' + sub)
data['sub'][sub] = {}
data['sub'][sub]['pub'] = get_publications(html)
data['sub'][sub]['name'] = jour[sub]
cnt += 1
print cnt, len(files), data['short']
util.save_json(save_path, data)
def get_journals():
files = util.listdir(JOURNAL_FOLDER)
util.mkdir(JOURNAL_CRALWED_FOLDER)
cnt = 0
jour = util.load_json('jour_name.json')
for file_name in files:
save_path = os.path.join(JOURNAL_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name))
if data['short'] not in jour.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = jour[data['short']]
data['sub'] = {}
for sub in subs:
html = util.get_page('http://dblp.uni-trier.de/db/journals/' + sub)
data['sub'][sub] = {}
data['sub'][sub]['pub'] = get_publications(html)
data['sub'][sub]['name'] = jour[sub]
cnt += 1
print cnt, len(files), data['short']
util.save_json(save_path, data)
def crawl_xroxy(self):
for i in ['CN', 'TW']:
start_url = 'http://www.xroxy.com/proxylist.php?country={}'.format(
i)
html = get_page(start_url)
if html:
ip_adress1 = re.compile(
"title='View this Proxy details'>\s*(.*).*")
re_ip_adress1 = ip_adress1.findall(html)
ip_adress2 = re.compile(
"title='Select proxies with port number .*'>(.*)</a>")
re_ip_adress2 = ip_adress2.findall(html)
for adress, port in zip(re_ip_adress1, re_ip_adress2):
adress_port = adress + ':' + port
yield adress_port.replace(' ', '')
def crawl_iphai(self):
start_url = 'http://www.iphai.com/'
html = get_page(start_url)
if html:
find_tr = re.compile('<tr>(.*?)</tr>', re.S)
trs = find_tr.findall(html)
for s in range(1, len(trs)):
find_ip = re.compile('<td>\s+(\d+\.\d+\.\d+\.\d+)\s+</td>',
re.S)
re_ip_address = find_ip.findall(trs[s])
find_port = re.compile('<td>\s+(\d+)\s+</td>', re.S)
re_port = find_port.findall(trs[s])
for address, port in zip(re_ip_address, re_port):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def crawl_ip3366(self):
for i in range(1, 4):
start_url = 'http://www.ip3366.net/?stype=1&page={}'.format(i)
html = get_page(start_url)
if html:
find_tr = re.compile('<tr>(.*?)</tr>', re.S)
trs = find_tr.findall(html)
for s in range(1, len(trs)):
find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>')
re_ip_address = find_ip.findall(trs[s])
find_port = re.compile('<td>(\d+)</td>')
re_port = find_port.findall(trs[s])
for address, port in zip(re_ip_address, re_port):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def crawl_kuaidaili(self):
for i in range(1, 4):
start_url = [
'http://www.kuaidaili.com/free/{}/{}/'.format(style, i)
for style in ['intr', 'inha']
]
for url in start_url:
html = get_page(url)
if html:
ip_address = re.compile('<td data-title="IP">(.*?)</td>')
re_ip_address = ip_address.findall(html)
port = re.compile('<td data-title="PORT">(.*?)</td>')
re_port = port.findall(html)
for address, port in zip(re_ip_address, re_port):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def get_conferences(): files = util.listdir(CONFERENCE_FOLDER) util.mkdir(CONFERENCE_CRALWED_FOLDER) cnt = 0 for file_name in files: cnt += 1 if cnt < 1970: continue save_path = os.path.join(CONFERENCE_CRALWED_FOLDER, file_name) data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name)) html = util.get_page(data['url']) full_name = get_full_name(html) data['name'] = full_name try: print cnt, len(files), data['short'] except: pass data['links'] = get_links(data['short'], html)
def load_stories(self):
if self.stories is None:
print('Loading story urls for', self.shelf)
s = []
for page in range(self.pages):
print('Loading page', page, 'out of', self.pages, 'for', self.shelf)
soup = self.first_page if page == 0 else bs4.BeautifulSoup(get_page(self.shelf, page + 1, LIST_VIEW), 'lxml')
bold_tags = soup(class_="search_results_count")[0]('b')
from_ = int(bold_tags[0].string)
to = int(bold_tags[1].string)
# there are 1-60 stories on the first page which means 60, but 60-1=59 so we add one
count = (to - from_) + 1
story_list = soup(class_="story-list")[0]('li')
for story in story_list:
s.append(story(class_="right")[0].h2.a['href'])
self.stories = tuple(s)
print(number_objects(len(self.stories), 'url(|s)'), 'loaded for', self.shelf)
return self.stories
def get_conferences():
files = util.listdir(CONFERENCE_FOLDER)
util.mkdir(CONFERENCE_CRALWED_FOLDER)
cnt = 0
for file_name in files:
cnt += 1
if cnt < 1970:
continue
save_path = os.path.join(CONFERENCE_CRALWED_FOLDER, file_name)
data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name))
html = util.get_page(data['url'])
full_name = get_full_name(html)
data['name'] = full_name
try:
print cnt, len(files), data['short']
except:
pass
data['links'] = get_links(data['short'], html)
def cb():
url = "http://esf.cq.fang.com"
#url,html = util.get_page({"url":url})
html = open("data/esf.html").read()
entries = get_entry(html)
fp = open("data/result.txt","a")
for entry in entries:
if entry[0] is None:
continue
eurl = util.parse_url(url,entry[0])
html = open("data/yubei.html").read()
eurl,html = util.get_page()
subs = get_sub(html)
for sub in subs:
surl = util.parse_url(eurl,sub[0])
if surl == eurl:
continue
html = open("data/list.html").read()
nurl,items = get_list(html,surl)
fp.close()
def get_conferences():
files = util.listdir(CONFERENCE_FOLDER)
util.mkdir(CONFERENCE_CRALWED_FOLDER)
cnt = 0
conf = util.load_json('conf_name.json')
for file_name in files:
save_path = os.path.join(CONFERENCE_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name))
if data['short'] not in conf.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = conf[data['short']]
data['sub'] = {}
if len(subs) == 0:
data['sub']['#'] = get_publications(html)
util.save_json(save_path, data)
cnt += 1
def get_conferences():
files = util.listdir(CONFERENCE_FOLDER)
util.mkdir(CONFERENCE_CRALWED_FOLDER)
cnt = 0
conf = util.load_json('conf_name.json')
for file_name in files:
save_path = os.path.join(CONFERENCE_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(CONFERENCE_FOLDER, file_name))
if data['short'] not in conf.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = conf[data['short']]
data['sub'] = {}
if len(subs) == 0:
data['sub']['#'] = get_publications(html)
util.save_json(save_path, data)
cnt += 1
def mail_fetch(mail_domain):
regex_domain = mail_domain.replace(".", "\\.").replace("-", "\\-")
this_regex = mail_regex + regex_domain
keyword = '"@%s"' % mail_domain
mails = []
for result in search(keyword):
logging.info(result)
try:
text = get_page(result)
except:
logging.info(traceback.format_exc())
pass
matchs = re.findall(this_regex, text)
matchs = list(set(matchs))
for match in matchs:
logging.info(match)
mails.append(match)
return list(set(mails))
def get_journals():
files = util.listdir(JOURNAL_FOLDER)
util.mkdir(JOURNAL_CRALWED_FOLDER)
cnt = 0
jour = util.load_json('jour_name.json')
for file_name in files:
save_path = os.path.join(JOURNAL_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name))
if data['short'] not in jour.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = jour[data['short']]
data['sub'] = {}
if len(subs) == 0:
data['sub']['#'] = get_publications(html)
util.save_json(save_path, data)
cnt += 1
print cnt, len(files), data['short']
def get_journals():
files = util.listdir(JOURNAL_FOLDER)
util.mkdir(JOURNAL_CRALWED_FOLDER)
cnt = 0
jour = util.load_json('jour_name.json')
for file_name in files:
save_path = os.path.join(JOURNAL_CRALWED_FOLDER, file_name)
if util.exists(save_path):
continue
data = util.load_json(os.path.join(JOURNAL_FOLDER, file_name))
if data['short'] not in jour.keys():
continue
html = util.get_page(data['url'])
subs = get_subs(data['short'], html)
data['name'] = jour[data['short']]
data['sub'] = {}
if len(subs) == 0:
data['sub']['#'] = get_publications(html)
util.save_json(save_path, data)
cnt += 1
print cnt, len(files), data['short']
def get_article(url,referer,data,fp,result2):
url, h = util.get_page({"url":url,"headers":{"Referer":referer}})
tree = etree.HTML(h)
scripts = [o for o in tree.xpath("//script/text()") if o.find("BASE_DATA") > -1 or o.find("__pgcInfo")>-1]
scripts.append("console.log(JSON.stringify(BASE_DATA))")
open("data/tmp.js","w").write("\n".join(scripts))
r = get_params("data/tmp.js")
if r is not None:
mp = json.loads(r)
obj = {"entry":data,"data":mp}
conf = [("title",["data","artilceInfo","title"]),
("content",["data","artilceInfo","content"],None,html.unescape),
("comments",["data","commentInfo","comments_count"],0),
("isOriginal",["data","artilceInfo","subInfo","isOriginal"],False),
("url",["__const",url]),
("views",["entry","go_detail_count"], 0),
("cover",["entry","image_url"],""),
("abstract",["entry","abstract"], ""),
("source",["data","artilceInfo","subInfo","source"],""),
("publishtime",["data","artilceInfo","subInfo","time"]),
("tags",["data","artilceInfo","tagInfo","tags"],"",lambda o:",".join([so["name"] for so in o])),
("category",["data","headerInfo","chineseTag"],""),
]
result = {}
for cf in conf:
v = util.get_jpath(obj,cf[1],cf[2] if len(cf)>2 else None,cf[3] if len(cf)>3 else None)
if v is not None:
result[cf[0]] = v
result["id"] = hashlib.md5(url.encode("utf-8")).hexdigest()
if "content" in result:
result["content"],result["images"] = replace_image(result["content"],url)
if "cover" in result and len(result["cover"])>0:
result["cover"] = imge_transfer(util.parse_url(url,result["cover"]),url)[1]
if len(result) > 0:
result2.append(result)
else:
util.log_msg("could not parse content from html file,need to check this out.url:%s,referer:%s." % (url,referer))
else:
util.log_msg("could not parse data from html file,need to check this out.url:%s,referer:%s." % (url,referer))
def get_authors():
pos, cnt = 545504, 0
util.mkdir(AUTHOR_FOLDER)
while True:
html = util.get_page(AUTHOR_URL + str(pos))
links = util.find_authors(html)
once_cnt = 0
for link in links:
if link[0] == '' or '?' in link[0]:
continue
data = {}
data['type'] = 'author'
data['short'] = link[0]
data['name'] = link[1]
data['url'] = 'http://dblp.uni-trier.de/pers/hd/a/' + data['short']
util.save_json(os.path.join(AUTHOR_FOLDER, util.hex_hash(data['short'])), data)
cnt += 1
once_cnt += 1
if once_cnt == 0:
break
pos += 300
print 'Author', pos, cnt
def get_conferences():
pos, cnt = 1, 0
util.mkdir(CONFERENCE_FOLDER)
while True:
html = util.get_page(CONFERENCE_URL + str(pos))
links = util.find_conferences(html)
once_cnt = 0
for link in links:
if link[0] == '' or '?' in link[0]:
continue
data = {}
data['type'] = 'conference'
data['short'] = link[0]
data['name'] = link[1]
data['url'] = 'http://dblp.uni-trier.de/db/conf/' + data['short']
util.save_json(os.path.join(CONFERENCE_FOLDER, util.hex_hash(data['short'])), data)
cnt += 1
once_cnt += 1
if once_cnt == 0:
break
pos += 100
print 'Conference', cnt
def get_journals():
pos, cnt = 1, 0
util.mkdir(JOURNAL_FOLDER)
while True:
html = util.get_page(JOURNAL_URL + str(pos))
links = util.find_journals(html)
once_cnt = 0
for link in links:
if link[0] == '' or '?' in link[0]:
continue
data = {}
data['type'] = 'journal'
data['short'] = link[0]
data['name'] = link[1]
data['url'] = 'http://dblp.uni-trier.de/db/journals/' + data['short']
util.save_json(os.path.join(JOURNAL_FOLDER, util.hex_hash(data['short'])), data)
cnt += 1
once_cnt += 1
if once_cnt == 0:
break
pos += 100
print 'Journal', cnt
def get_authors():
pos, cnt = 545504, 0
util.mkdir(AUTHOR_FOLDER)
while True:
html = util.get_page(AUTHOR_URL + str(pos))
links = util.find_authors(html)
once_cnt = 0
for link in links:
if link[0] == '' or '?' in link[0]:
continue
data = {}
data['type'] = 'author'
data['short'] = link[0]
data['name'] = link[1]
data['url'] = 'http://dblp.uni-trier.de/pers/hd/a/' + data['short']
util.save_json(
os.path.join(AUTHOR_FOLDER, util.hex_hash(data['short'])),
data)
cnt += 1
once_cnt += 1
if once_cnt == 0:
break
pos += 300
print 'Author', pos, cnt
def crawl_xicidaili(self):
for i in range(1, 3):
start_url = 'http://www.xicidaili.com/nn/{}'.format(i)
headers = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Cookie':
'_free_proxy_session=BAh7B0kiD3Nlc3Npb25faWQGOgZFVEkiJWRjYzc5MmM1MTBiMDMzYTUzNTZjNzA4NjBhNWRjZjliBjsAVEkiEF9jc3JmX3Rva2VuBjsARkkiMUp6S2tXT3g5a0FCT01ndzlmWWZqRVJNek1WanRuUDBCbTJUN21GMTBKd3M9BjsARg%3D%3D--2a69429cb2115c6a0cc9a86e0ebe2800c0d471b3',
'Host': 'www.xicidaili.com',
'Referer': 'http://www.xicidaili.com/nn/3',
'Upgrade-Insecure-Requests': '1',
}
html = get_page(start_url, options=headers)
if html:
find_trs = re.compile('<tr class.*?>(.*?)</tr>', re.S)
trs = find_trs.findall(html)
for tr in trs:
find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>')
re_ip_address = find_ip.findall(tr)
find_port = re.compile('<td>(\d+)</td>')
re_port = find_port.findall(tr)
for address, port in zip(re_ip_address, re_port):
address_port = address + ':' + port
yield address_port.replace(' ', '')
def cb():
'''
url = "https://www.facebook.com/"
url,html = util.get_page({"url":url})
#print(html)
##print(type(html))
open("data/facebook.html","w").write(html)
#html = open("data/facebook.html").read()
ts = int(time.time())
lsd = re.findall("name=\"lsd\" value=\"[^\"]+\"", html)
lsd = lsd[0].split("\"")[3] if len(lsd) > 0 else None
lgnrnd = re.findall("name=\"lgnrnd\" value=\"[^\"]+\"",html)
lgnrnd = lgnrnd[0].split("\"")[3] if len(lgnrnd) > 0 else None
if lsd is None or lgnrnd is None:
print("could not parse lsd")
sys.exit(0)
data = {
"lsd":lsd,
"email":"*****@*****.**",
"pass":"******",
"timezone":-480,
"lgndim":"eyJ3IjoxOTIwLCJoIjoxMDgwLCJhdyI6MTkyMCwiYWgiOjEwNTMsImMiOjI0fQ==",
"lgnrnd":lgnrnd,
"lgnjs":ts,
"ab_test_data":"AA///AAAAAAAA/A/AAA/AAAAAAAAAAAAAAAAAAAAAAAAf//fA/DBAB",
"locale":"zh_CN",
"login_source":"login_bluebar",
}
url = "https://www.facebook.com/login.php?login_attempt=1&lwv=110"
url,html = util.get_page({"url":url,"data":data})
open("data/facebook2.html","w").write(html)
#url = "https://www.facebook.com/100008346345446"
url = "https://www.facebook.com/profile.php?id=100008346345446"
url,html = util.get_page({"url":url})
print(url)
open("data/profile2.html","w").write(html)
'''
'''
c_id = "100014233620831"
uid = "100008346345446"
ts = int(time.time())
url = "https://www.facebook.com/profile.php?id=%s&lst=%s%%3A%s%%3A%d&sk=friends&source_ref=pb_friends_tl" % (uid,c_id,uid,ts)
url,html = util.get_page({"url":url})
print(url)
open("data/friends.html","w").write(html)
'''
params = {
"dpr":"1",
"__user":"******",
"__a":"1",
"__dyn":"7AgNeyfyGmaxx2u6aEyx91qeCwKAKGgyi8zQC-C267UKewWhE98nwgUy22EaUgxebkwy8xa5WjzEgDKuEjKewExaFQ12VVojxCUSbAWCDxi5-78O5u5o5aayrhVo9ohxGbwYUmC-UjDQ6Evwwh8gUW5oy5EG2ut5xq48a9Ef8Cu4rGUpCzo-8Gm8z8O784afxK9yUvy8lUGdyU4eQEB0",
"__af":"j0",
"__req":"26",
"__be":"-1",
"__pc":"EXP4:DEFAULT",
"__rev":"3161010",
"__spin_r":"3161010",
"__spin_b":"trunk",
"__spin_t":"1500360303"
}
content = open("data/friends.html").read()
data,info = get_info(content,None)
params["data"] = data
ts = int(time.time())
params["__spin_t"] = ts
url = "https://www.facebook.com/ajax/pagelet/generic.php/AllFriendsAppCollectionPagelet"
url,html = util.get_page({"url":url,"data":params})
print(url)
open("data/friends_page.html","w").write(html)
def get(url,fname):
url,html = util.get_page({"url":url})
open(fname,"w").write(html)
