def analysis_html(html, url_pattern, title_pattern):
url_list = re.findall(url_pattern, html)
title_list = re.findall(title_pattern, html)
i = 0
while i < len(url_list):
url_list[i] = url_list[i]
title_list[i] = title_list[i][7:].replace('</span>', '')
title_list[i] = aesDecrypt('YhG78Plkl56Htrqw', title_list[i])
i += 1
return url_list, title_list
def paquindex(url, key):
html = load_url(url)
name_pattern = r'[te]" id="detxt">.{10,100}</span>'
url_pattern = r'listde.php\?act=list&aid=[0-9]{2,3}'
name_list = re.findall(name_pattern, html)
url_list = re.findall(url_pattern, html)
i = 0
while i < len(url_list):
url_list[i] = url_list[i].replace('"', '')
name_list[i] = name_list[i][14:].replace('</span>', '')
name_list[i] = aesDecrypt(key, name_list[i])
nameArray.append(name_list[i])
urlArray.append(url_list[i])
i += 1
def paqu(url, filepath, name, tag, insertSql ):
key = 'YhG78Plkl56Htrqw'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36'
}
reponse = requests.get(url, headers=headers)
time.sleep(1)
txt = reponse.content.decode("utf-8", errors="ignore")
if 'Warning' in txt:
tag = False
return tag
img = txt[txt.find(' = "') + 4:]
img = aesDecrypt(key, img)
if not os.path.exists(filepath):
os.makedirs(filepath)
with open(filepath+'/'+name + '.png', 'wb') as f:
f.write(base64.b64decode(img))
insertsql(insertSql)
return tag