def download_bd_info(name, dst):
ofile = os.path.join(dst, u"{}_bd.txt".format(name))
if os.path.exists(ofile):
print(u'Baidu Skip {}'.format(name))
return ofile
bd_url = BD_URL.format(name)
bd_text = None
r = commons.get(bd_url, encoding='utf-8',
allow_redirects=False)
if r.status_code == 200:
bd_text = parse_bd_text(r.text)
elif r.status_code == 302:
location = r.headers['Location']
if location and location.startswith('/item/'):
bd_url = "{}{}".format(BD_HOST, location)
r = commons.get(bd_url, encoding='utf-8',
allow_redirects=False)
if r.status_code == 200:
bd_text = parse_bd_text(r.text)
else:
if name.endswith(u'鱼'):
bd_url = BD_URL.format(name[:-1])
r = commons.get(bd_url, encoding='utf-8',
allow_redirects=False)
if r.status_code == 200:
bd_text = parse_bd_text(r.text)
if bd_text:
with codecs.open(ofile, 'w', 'utf-8') as f:
print(u'Baidu Found {}'.format(name))
f.write(bd_url)
f.write('\n\n')
f.write(bd_text)
return ofile
def download_fish_list(list_file, dst=None):
if not dst:
dst = os.path.dirname(list_file)
names = codecs.open(list_file, 'r', encoding='utf-8').read().splitlines()
for name in names:
url = LS_URL.format(name)
r = commons.get(url, encoding='utf-8', allow_redirects=False)
if r.status_code != 200 or not r.text:
print(u'No match {}'.format(name))
continue
url = LS_INFO_URL.format(r.text)
# print(url)
r = commons.get(url, encoding='utf-8',
allow_redirects=False)
if r.status_code != 200:
continue
title, content = parse_ls_text(r.text)
if title and content:
ofile = os.path.join(dst, u'{}.txt'.format(title))
if os.path.exists(ofile):
print(u'Skip {}'.format(title))
continue
with codecs.open(ofile, 'w', 'utf-8') as f:
print(u'Saved {}'.format(title))
f.write(content)
def download_hd_info(name, dst):
ofile = os.path.join(dst, u"{}_hd.txt".format(name))
if os.path.exists(ofile):
print(u'Hudong Skip {}'.format(name))
return ofile
hd_url = HD_URL.format(name)
hd_text = None
r = commons.get(hd_url, encoding='utf-8',
allow_redirects=False)
if r.status_code == 200:
hd_text = parse_hd_text(r.text)
if hd_text:
with codecs.open(ofile, 'w', 'utf-8') as f:
print(u'Hudong Found {}'.format(name))
f.write(hd_url)
f.write('\n\n')
f.write(hd_text)
return ofile
def download_csdb_info(name, dst):
ofile = os.path.join(dst, u"{}_csdb.txt".format(name))
if os.path.exists(ofile):
print(u'CSDB Skip {}'.format(name))
return ofile
csdb_url = get_csdb_url(name)
csdb_text = None
if csdb_url:
r = commons.get(csdb_url, encoding='utf-8',
allow_redirects=False)
if r.status_code == 200:
csdb_text = parse_csdb_text(r.text)
if csdb_text:
with codecs.open(ofile, 'w', 'utf-8') as f:
print(u'CSDB Found {}'.format(name))
f.write(csdb_url)
f.write('\n\n')
f.write(csdb_text)
return ofile
def get_csdb_url(name):
exclude = [u'属', u'科', u'目', u'蚊', u'蛾', u'虫']
r = commons.get(CSDB_URL.format(name), encoding='utf-8',
allow_redirects=False)
if r.status_code == 200:
soup = BeautifulSoup(r.text, "lxml")
result = None
for s in soup.find_all(csdb_info_link):
skip = False
for e in exclude:
if e in s.text:
skip = True
break
if skip:
continue
if name in s.text:
result = s['href']
break
if result:
return CSDB_HOST + result
def test_index():
url = 'http://127.0.0.1:5000/bill_type'
get(url)
pass
def test_detail():
url = 'http://127.0.0.1:5000/bill_type/detail/1'
get(url)
pass
def test_list():
url = 'http://127.0.0.1:5000/bill_type/list'
get(url)
pass
def test_detail():
url = 'http://127.0.0.1:5000/bill/detail/1'
get(url)
pass
def test_index():
url = 'http://127.0.0.1:5000/bill'
get(url)
pass
def test_list():
url = 'http://127.0.0.1:5000/bill/list'
get(url)
pass
def test_index():
url = 'http://127.0.0.1:5000/user'
get(url)
pass
def test_detail():
url = 'http://127.0.0.1:5000/user/detail/1'
get(url)
pass
def test_list():
url = 'http://127.0.0.1:5000/user/list'
get(url)
pass
def detail(poll_id):
raw = get("polls/"+str(poll_id)+"/")
final = dict()
for x in raw:
final[int(x)] = raw[x]
return final