Python urllib 模块，URLError() 实例源码

def rank_checker(url,hatebu_url):
    try:
        html = request.urlopen(hatebu_url)
    except request.HTTPError as e:
        print(e.reason)
    except request.URLError as e:
        print(e.reason)
    soup = BeautifulSoup(html,"lxml")
    a = soup.find("a",href=url)
    if a == None:
        rank = None
    else:
        rank = a.get("data-entryrank")
    return rank

# ????????????????????

def prepare(self, first_url):
        tmp_cookie = http.cookiejar.CookieJar()
        opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(tmp_cookie))
        try:
            response = opener.open(self.logout_url, timeout=3)
        except urllib.HTTPError as e:
            logging.warn("server process request error: err_code=%s", e.code)
            return -5, None
        except urllib.URLError as e:
            logging.warn("reach server error: reason=%s", e.reason)
            return -10, None
        except Exception as e:
            logging.warn("other exception: msg=%s", e.message)
            return -100, None

        for item in tmp_cookie:
            self.my_cookie+=item.name + "=" +item.value + ";"
        #htm = response.read()
        return 0, None

    ########## post data to request_url ##############

def get_category(url):
    try:
        html = request.urlopen("http://b.hatena.ne.jp/entry/{}".format(url))
        soup = BeautifulSoup(html,"lxml")
        return soup.find("html").get("data-category-name")
    except request.HTTPError as e:
        print(e.reason)
    except request.URLError as e:
        print(e.reason)

#??????????????????

def is_hatenatop(url):
    try:
        html = request.urlopen("http://hatenablog.com/")
    except urllib.HTTPError as e:
        print(e.reason)
    except urllib.URLError as e:
        print(e.reason)
    soup = BeautifulSoup(html,"lxml")
    a = soup.find("a",href=url)
    if a is None:
        return False
    return url == a.get("href")

def crawl_detail(self):           #????????????
        for ipo in self.ipo_list:
            attr_report(446076)
            url = self.detail_url % ipo["code"]
            req = urllib.request.Request(
                url=url,
            )
            req.add_header('User-agent', user_agent)

            retry_cnt = 0
            while retry_cnt < 3:
                try:
                    try:
                        resp = urllib.request.urlopen(req, timeout=3)
                    except urllib.HTTPError as e:
                        logging.warning("server process request error: err_code=%s", e.code)
                        return -5, None
                    except urllib.URLError as e:
                        logging.warning("reach server error: reason=%s", e.reason)
                        return -10, None
                    except Exception as e:
                        logging.warning("other exception: msg=%s", e.message)
                        return -100, None

                    html_text = resp.read().decode("gbk")
                    resp.close()
                    if self._parse_detail(html_text, ipo):
                        break
                    else:
                        retry_cnt += 1
                except Exception as e:
                    retry_cnt += 1
                    logging.warning('cn craw {0} detail ex:{1}, {2}'.format(ipo["code"], e, traceback.format_exc()))
            if retry_cnt >= 3:
                attr_report(441846)
                logging.info("cn craw {0} detail fail".format(ipo["code"]))
            else:
                attr_report(441845)

def post_to_url(self, request_url, post_data):
        post_encode = urlencode(post_data).encode()
        #print post_encode
        req = urllib.request.Request(
            url=request_url,
            data=post_encode
            )
        req.add_header('Cookie', self.my_cookie)
        #print req.headers
        #print req.data
        try:
            resp = urllib.request.urlopen(req, timeout=3)
        except urllib.error.HTTPError as e:
            logging.warn("server process request error: err_code=%s", e.code)
            return -5, None
        except urllib.error.URLError as e:
            logging.warn("reach server error: reason=%s", e.reason)
            return -10, None
        except Exception as e:
            logging.warn("other exception: msg=%s", e.__str__())
            return -100, None

        htm = resp.read()
        return 0, htm

    ########## get data to request_url ###############

def get_to_url(self, request_url, get_data):
        if get_data == "":
            tmp_url = request_url
        else:
            tmp_url = request_url + "?" + get_data
        #print tmp_url
        #print self.my_cookie
        req = urllib.request.Request(
            url=request_url,
            )
        req.add_header('Cookie', self.my_cookie)
        #print req.headers
        #print req.data
        try:
            resp = urllib.request.urlopen(req, timeout=3)
        except urllib.HTTPError as e:
            logging.warn("server process request error: err_code=%s", e.code)
            return -5, None
        except urllib.URLError as e:
            logging.warn("reach server error: reason=%s", e.reason)
            return -10, None
        except Exception as e:
            logging.warn("other exception: msg=%s", e.message)
            return -100, None

        htm = resp.read()
        return 0, htm

def _fetch_url(self):
        try:
            r = urllib
            data = r.read()
            self.f = xio.StringIO(data)
            self._fetched = True
        except urllib.URLError:
            return self.fetch_next_server()