How to use akshare - 10 common examples

def interest_over_time(self):
        """Request data from Google's Interest Over Time section and return a dataframe"""

        over_time_payload = {
            # convert to string as requests will mangle
            "req": json.dumps(self.interest_over_time_widget["request"]),
            "token": self.interest_over_time_widget["token"],
            "tz": self.tz,
        }

        # make the request and parse the returned json
        req_json = self._get_data(
            url=TrendReq.INTEREST_OVER_TIME_URL,
            method=TrendReq.GET_METHOD,
            trim_chars=5,
            params=over_time_payload,
        )

        df = pd.DataFrame(req_json["default"]["timelineData"])
        if df.empty:
            return df

        df["date"] = pd.to_datetime(df["time"].astype(dtype="float64"), unit="s")
        df = df.set_index(["date"]).sort_index()
        # split list columns into seperate ones, remove brackets and split on comma
        result_df = df["value"].apply(
            lambda x: pd.Series(str(x).replace("[", "").replace("]", "").split(","))
        )
        # rename each column with its search term, relying on order that google provides...

def bank_page_list(page=5):
    """
    想要获取多少页的内容
    注意路径
    http://www.cbirc.gov.cn/cn/list/9103/910305/ybjfjcf/1.html
    :param page: int 输入从第 1 页到 all_page 页的内容
    :return: pd.DataFrame 另存为 csv 文件
    """
    big_url_list = []
    big_title_list = []
    flag = True
    cbirc_headers = cbirc_headers_without_cookie_2019.copy()
    for i_page in range(1, page):
        # i_page = 1
        print(i_page)
        main_url = "http://www.cbirc.gov.cn/cn/list/9103/910305/ybjfjcf/{}.html".format(
            i_page
        )
        if flag:
            res = requests.get(main_url, headers=cbirc_headers)
            temp_cookie = res.headers["Set-Cookie"].split(";")[0]
            cbirc_headers.update({"Cookie": res.headers["Set-Cookie"].split(";")[0]})
            res = requests.get(main_url, headers=cbirc_headers)
            soup = BeautifulSoup(res.text, "lxml")
            res_html = (
                "function getClearance(){"
                + soup.find_all("script")[0].get_text()
                + "};"

"""
    if indicator:
        if source or topic:
            raise ValueError(INDIC_ERROR)
        query_url = "/".join((INDICATOR_URL, parse_value_or_iterable(indicator)))
    elif source:
        if topic:
            raise ValueError(INDIC_ERROR)
        query_url = "/".join(
            (SOURCES_URL, parse_value_or_iterable(source), "indicators")
        )
    elif topic:
        query_url = "/".join((TOPIC_URL, parse_value_or_iterable(topic), "indicators"))
    else:
        query_url = INDICATOR_URL
    return WBSearchResult(fetcher.fetch(query_url, cache=cache))

def id_only_query(query_url, query_id, cache):
    """
    Retrieve information when ids are the only arguments

    :query_url: the base url to use for the query
    :query_id: an id or sequence of ids
    :cache: use the cache
    :returns: WBSearchResult containing dictionary objects describing results
    """
    if query_id:
        query_url = "/".join((query_url, parse_value_or_iterable(query_id)))
    return WBSearchResult(fetcher.fetch(query_url))

:incomelevel: desired incomelevel id or ids.
    :lendingtype: desired lendingtype id or ids.
    :cache: use the cache
    :returns: WBSearchResult containing dictionary objects representing each
        country
    """
    if country_id:
        if incomelevel or lendingtype:
            raise ValueError("Can't specify country_id and aggregates")
        return id_only_query(COUNTRIES_URL, country_id, cache=cache)
    args = {}
    if incomelevel:
        args["incomeLevel"] = parse_value_or_iterable(incomelevel)
    if lendingtype:
        args["lendingType"] = parse_value_or_iterable(lendingtype)
    return WBSearchResult(fetcher.fetch(COUNTRIES_URL, args, cache=cache))

query_url = COUNTRIES_URL
    try:
        c_part = parse_value_or_iterable(country)
    except TypeError:
        raise TypeError("'country' must be a string or iterable'")
    query_url = "/".join((query_url, c_part, "indicators", indicator))
    args = {}
    if data_date:
        if isinstance(data_date, collections.Sequence):
            data_date_str = ":".join((i.strftime("%Y") for i in data_date))
            args["date"] = data_date_str
        else:
            args["date"] = data_date.strftime("%Y")
    if source:
        args["source"] = source
    data = fetcher.fetch(query_url, args, cache=cache)
    if convert_date:
        data = convert_dates_to_datetime(data)
    return data

def suggestions(self, keyword):
        """Request data from Google's Keyword Suggestion dropdown and return a dictionary"""

        # make the request
        kw_param = quote(keyword)
        parameters = {"hl": self.hl}

        req_json = self._get_data(
            url=TrendReq.SUGGESTIONS_URL + kw_param,
            params=parameters,
            method=TrendReq.GET_METHOD,
            trim_chars=5,
        )["default"]["topics"]
        return req_json

def _tokens(self):
        """Makes request to Google to get API tokens for interest over time, interest by region and related queries"""
        # make the request and parse the returned json
        widget_dict = self._get_data(
            url=TrendReq.GENERAL_URL,
            method=TrendReq.GET_METHOD,
            params=self.token_payload,
            trim_chars=4,
        )["widgets"]
        # order of the json matters...
        first_region_token = True
        # clear self.related_queries_widget_list and self.related_topics_widget_list
        # of old keywords'widgets
        self.related_queries_widget_list[:] = []
        self.related_topics_widget_list[:] = []
        # assign requests
        for widget in widget_dict:
            if widget["id"] == "TIMESERIES":
                self.interest_over_time_widget = widget
            if widget["id"] == "GEO_MAP" and first_region_token:
                self.interest_by_region_widget = widget

def categories(self):
        """Request available categories data from Google's API and return a dictionary"""

        params = {"hl": self.hl}

        req_json = self._get_data(
            url=TrendReq.CATEGORIES_URL,
            params=params,
            method=TrendReq.GET_METHOD,
            trim_chars=5,
        )
        return req_json

def trending_searches(self, pn="united_states"):
        """Request data from Google's Hot Searches section and return a dataframe"""

        # make the request
        # forms become obsolute due to the new TRENDING_SEACHES_URL
        # forms = {'ajax': 1, 'pn': pn, 'htd': '', 'htv': 'l'}
        req_json = self._get_data(
            url=TrendReq.TRENDING_SEARCHES_URL, method=TrendReq.GET_METHOD
        )[pn]
        result_df = pd.DataFrame(req_json)
        return result_df