Python TypeError: 'NoneType' object is not iterable -

Python TypeError: 'NoneType' object is not iterable -

i have looked @ other posts seem have same problem me, issue has not been resolved yet ...

i trying extract google page rank list of domain names, in case "domain_list". below code using. maintain getting error , cannot figure out underlying reason it.

import struct import sys import urllib import urllib2 import httplib import re import xml.etree.elementtree domain_list = open('/data/personal/samaneh/test.txt','r') class rankprovider(object): """abstract class obtaining page rank (popularity) provider such google or alexa. """ def __init__(self, host, proxy=none, timeout=30): """keyword arguments: host -- toolbar host address proxy -- address of proxy server. default: none timeout -- how long wait response server. default: 30 (seconds) """ self._opener = urllib2.build_opener() if proxy: self._opener.add_handler(urllib2.proxyhandler({"http": proxy})) self._host = host self._timeout = timeout def get_rank(self, url): """get page rank specified url keyword arguments: url -- page rank url """ raise notimplementederror("you must override get_rank()") class alexatrafficrank(rankprovider): """ alexa traffic rank url """ def __init__(self, host="xml.alexa.com", proxy=none, timeout=30): """keyword arguments: host -- toolbar host address: default: joolbarqueries.google.com proxy -- address of proxy server (if required). default: none timeout -- how long wait response server. default: 30 (seconds) """ super(alexatrafficrank, self).__init__(host, proxy, timeout) def get_rank(self, url): """get page rank specified url keyword arguments: url -- page rank url """ query = "http://%s/data?%s" % (self._host, urllib.urlencode(( ("cli", 10), ("dat", "nsa"), ("ver", "quirk-searchstatus"), ("uid", "20120730094100"), ("userip", "192.168.0.1"), ("url", url)))) response = self._opener.open(query, timeout=self._timeout) if response.getcode() == httplib.ok: info = response.read() element = xml.etree.elementtree.fromstring(data) e in element.find("sd"): popularity = e.find("popularity") if popularity not none: homecoming int(popularity.get("text")) class googlepagerank(rankprovider): """ google page rank figure using toolbar api. credits author of www::google::pagerank cpan bundle ported code python. """ def __init__(self, host="toolbarqueries.google.com", proxy=none, timeout=30): """keyword arguments: host -- toolbar host address: default: toolbarqueries.google.com proxy -- address of proxy server (if required). default: none timeout -- how long wait response server. default: 30 (seconds) """ super(googlepagerank, self).__init__(host, proxy, timeout) self._opener.addheaders = [("user-agent", "mozilla/4.0 (compatible; \ googletoolbar 2.0.111-big; windows xp 5.1)")] def get_rank(self, url): # calculate hash required part of # request sent toolbarqueries url. ch = '6' + str(self._compute_ch_new("info:%s" % (url))) query = "http://%s/tbr?%s" % (self._host, urllib.urlencode(( ("client", "navclient-auto"), ("ch", ch), ("ie", "utf-8"), ("oe", "utf-8"), ("features", "rank"), ("q", "info:%s" % (url))))) response = self._opener.open(query, timeout=self._timeout) if response.getcode() == httplib.ok: info = response.read() match = re.match("rank_\d+:\d+:(\d+)", data) if match: rank = match.group(1) homecoming int(rank) @classmethod def _compute_ch_new(cls, url): ch = cls._compute_ch(url) ch = ((ch % 0x0d) & 7) | ((ch / 7) << 2); homecoming cls._compute_ch(struct.pack("<20l", *(cls._wsub(ch, * 9) in range(20)))) @classmethod def _compute_ch(cls, url): url = struct.unpack("%db" % (len(url)), url) = 0x9e3779b9 b = 0x9e3779b9 c = 0xe6359a60 k = 0 length = len(url) while length >= 12: = cls._wadd(a, url[k+0] | (url[k+1] << 8) | (url[k+2] << 16) | (url[k+3] << 24)); b = cls._wadd(b, url[k+4] | (url[k+5] << 8) | (url[k+6] << 16) | (url[k+7] << 24)); c = cls._wadd(c, url[k+8] | (url[k+9] << 8) | (url[k+10] << 16) | (url[k+11] << 24)); a, b, c = cls._mix(a, b, c) k += 12 length -= 12 c = cls._wadd(c, len(url)); if length > 10: c = cls._wadd(c, url[k+10] << 24) if length > 9: c = cls._wadd(c, url[k+9] << 16) if length > 8: c = cls._wadd(c, url[k+8] << 8) if length > 7: b = cls._wadd(b, url[k+7] << 24) if length > 6: b = cls._wadd(b, url[k+6] << 16) if length > 5: b = cls._wadd(b, url[k+5] << 8) if length > 4: b = cls._wadd(b, url[k+4]) if length > 3: = cls._wadd(a, url[k+3] << 24) if length > 2: = cls._wadd(a, url[k+2] << 16) if length > 1: = cls._wadd(a, url[k+1] << 8) if length > 0: = cls._wadd(a, url[k]) a, b, c = cls._mix(a, b, c); # integer positive homecoming c @classmethod def _mix(cls, a, b, c): = cls._wsub(a, b); = cls._wsub(a, c); ^= c >> 13; b = cls._wsub(b, c); b = cls._wsub(b, a); b ^= (a << 8) % 4294967296; c = cls._wsub(c, a); c = cls._wsub(c, b); c ^= b >>13; = cls._wsub(a, b); = cls._wsub(a, c); ^= c >> 12; b = cls._wsub(b, c); b = cls._wsub(b, a); b ^= (a << 16) % 4294967296; c = cls._wsub(c, a); c = cls._wsub(c, b); c ^= b >> 5; = cls._wsub(a, b); = cls._wsub(a, c); ^= c >> 3; b = cls._wsub(b, c); b = cls._wsub(b, a); b ^= (a << 10) % 4294967296; c = cls._wsub(c, a); c = cls._wsub(c, b); c ^= b >> 15; homecoming a, b, c @staticmethod def _wadd(a, b): homecoming (a + b) % 4294967296 @staticmethod def _wsub(a, b): homecoming (a - b) % 4294967296 if __name__ == "__main__": url in domain_list: # url = "http://www.archlinux.org" providers = (alexatrafficrank(), googlepagerank(),) print("traffic stats for: %s" % (url)) p in providers: print("%s:%s" % (p.__class__.__name__, p.get_rank(url)))

and here finish error get:

traceback (most recent phone call last): file "test-alexa-ranking.py", line 187, in <module> print("%s:%s" % (p.__class__.__name__, p.get_rank(url))) file "test-alexa-ranking.py", line 69, in get_rank e in element.find("sd"): typeerror: 'nonetype' object not iterable

can help me that?

element.find() returns one match, if there one, otherwise returns none.

you either want utilize element.find_all(), homecoming list of matches (which can empty), or test first if there match:

match = element.find('sd') if not match: homecoming none

seeing looking contained element, utilize xpath expression here:

# find first popularity tag straight under sd tag text attribute pop = element.find('.//sd/popularity[@text]') if pop not none: homecoming int(pop.attrib['text'])

this looks work test xml document.

python typeerror