How to use the icrawler.Parser function in icrawler

return search_filter

    def feed(self, keyword, offset, max_num, filters=None):
        base_url = ('http://image.baidu.com/search/acjson?tn=resultjson_com'
                    '&ipn=rj&word={}&pn={}&rn=30')
        self.filter = self.get_filter()
        filter_str = self.filter.apply(filters, sep='&')
        for i in range(offset, offset + max_num, 30):
            url = base_url.format(keyword, i)
            if filter_str:
                url += '&' + filter_str
            self.out_queue.put(url)
            self.logger.debug('put url to url_queue: {}'.format(url))


class BaiduParser(Parser):

    def _decode_url(self, encrypted_url):
        url = encrypted_url
        map1 = {'_z2C$q': ':', '_z&e3B': '.', 'AzdH3F': '/'}
        map2 = {
            'w': 'a', 'k': 'b', 'v': 'c', '1': 'd', 'j': 'e',
            'u': 'f', '2': 'g', 'i': 'h', 't': 'i', '3': 'j',
            'h': 'k', 's': 'l', '4': 'm', 'g': 'n', '5': 'o',
            'r': 'p', 'q': 'q', '6': 'r', 'f': 's', 'p': 't',
            '7': 'u', 'e': 'v', 'o': 'w', '8': '1', 'd': '2',
            'n': '3', '9': '4', 'c': '5', 'm': '6', '0': '7',
            'b': '8', 'l': '9', 'a': '0'
        }  # yapf: disable
        for (ciphertext, plaintext) in map1.items():
            url = url.replace(ciphertext, plaintext)
        char_list = [char for char in url]

def __init__(self,
                 feeder_cls=Feeder,
                 parser_cls=Parser,
                 downloader_cls=Downloader,
                 feeder_threads=1,
                 parser_threads=1,
                 downloader_threads=1,
                 storage={
                     'backend': 'FileSystem',
                     'root_dir': 'images'
                 },
                 log_level=logging.INFO,
                 extra_feeder_args=None,
                 extra_parser_args=None,
                 extra_downloader_args=None):
        """Init components with class names and other arguments.

        Args:
            feeder_cls: class of feeder

# -*- coding: utf-8 -*-

import re

from bs4 import BeautifulSoup
from six.moves import html_parser

from icrawler import Crawler, Parser, SimpleSEFeeder, ImageDownloader


class BingParser(Parser):

    def parse(self, response):
        soup = BeautifulSoup(response.content, 'lxml')
        image_divs = soup.find_all('div', class_='imgpt')
        pattern = re.compile(r'murl\":\"(.*?)\.jpg')
        for div in image_divs:
            href_str = html_parser.HTMLParser().unescape(div.a['m'])
            match = pattern.search(href_str)
            if match:
                img_url = '{}.jpg'.format(match.group(1))
                yield dict(file_url=img_url)


class BingImageCrawler(Crawler):

    def __init__(self,

return search_filter

    def feed(self, keyword, offset, max_num, filters=None):
        base_url = 'https://www.bing.com/images/async?q={}&first={}'
        self.filter = self.get_filter()
        filter_str = self.filter.apply(filters)
        filter_str = '&qft=' + filter_str if filter_str else ''

        for i in range(offset, offset + max_num, 20):
            url = base_url.format(keyword, i) + filter_str
            self.out_queue.put(url)
            self.logger.debug('put url to url_queue: {}'.format(url))


class BingParser(Parser):

    def parse(self, response):
        soup = BeautifulSoup(
            response.content.decode('utf-8', 'ignore'), 'lxml')
        image_divs = soup.find_all('div', class_='imgpt')
        pattern = re.compile(r'murl\":\"(.*?)\.jpg')
        for div in image_divs:
            href_str = html_parser.HTMLParser().unescape(div.a['m'])
            match = pattern.search(href_str)
            if match:
                name = (match.group(1)
                        if six.PY3 else match.group(1).encode('utf-8'))
                img_url = '{}.jpg'.format(name)
                yield dict(file_url=img_url)

class GoogleFeeder(Feeder):

    def feed(self, keyword, offset, max_num, date_min, date_max):
        base_url = 'https://www.google.com/search?site=imghp&tbm=isch&source=hp&'
        for i in range(offset, offset + max_num, 100):
            cd_min = date_min.strftime('%d/%m/%Y') if date_min else ''
            cd_max = date_max.strftime('%d/%m/%Y') if date_max else ''
            tbs = 'cdr:1,cd_min:{},cd_max:{}'.format(cd_min, cd_max)
            params = dict(
                q=keyword, ijn=int(i / 100), start=i, tbs=tbs, tbm='isch')
            url = base_url + urlencode(params)
            self.out_queue.put(url)
            self.logger.debug('put url to url_queue: {}'.format(url))


class GoogleParser(Parser):

    def parse(self, response):
        soup = BeautifulSoup(response.content, 'lxml')
        image_divs = soup.find_all('div', class_='rg_meta')
        for div in image_divs:
            meta = json.loads(div.text)
            if 'ou' in meta:
                yield dict(file_url=meta['ou'])


class GoogleImageCrawler(Crawler):

    def __init__(self,
                 feeder_cls=GoogleFeeder,
                 parser_cls=GoogleParser,
                 downloader_cls=ImageDownloader,

filter_str = self.filter.apply(filters, sep=',')
        for i in range(offset, offset + max_num, 100):
            params = dict(
                q=keyword,
                ijn=int(i / 100),
                start=i,
                tbs=filter_str,
                tbm='isch')
            if language:
                params['lr'] = 'lang_' + language
            url = base_url + urlencode(params)
            self.out_queue.put(url)
            self.logger.debug('put url to url_queue: {}'.format(url))


class GoogleParser(Parser):

    def parse(self, response):
        soup = BeautifulSoup(
            response.content.decode('utf-8', 'ignore'), 'lxml')
        image_divs = soup.find_all('div', class_='rg_meta')
        for div in image_divs:
            meta = json.loads(div.text)
            if 'ou' in meta:
                yield dict(file_url=meta['ou'])


class GoogleImageCrawler(Crawler):

    def __init__(self,
                 feeder_cls=GoogleFeeder,
                 parser_cls=GoogleParser,

for i in range(page, page + page_max):
            if self.signal.get('reach_max_num'):
                break
            complete_url = '{}&page={}'.format(url, i)
            while True:
                try:
                    self.output(complete_url, block=False)
                except:
                    if self.signal.get('reach_max_num'):
                        break
                else:
                    break
            self.logger.debug('put url to url_queue: {}'.format(complete_url))


class FlickrParser(Parser):

    def parse(self, response, apikey, size_preference=None):
        content = json.loads(response.content.decode('utf-8', 'ignore'))
        if content['stat'] != 'ok':
            return
        photos = content['photos']['photo']
        for photo in photos:
            photo_id = photo['id']
            base_url = 'https://api.flickr.com/services/rest/?'
            params = {
                'method': 'flickr.photos.getSizes',
                'api_key': apikey,
                'photo_id': photo_id,
                'format': 'json',
                'nojsoncallback': 1
            }

import threading

from six.moves import queue

from icrawler import Crawler, Parser, UrlListFeeder, ImageDownloader


class PseudoParser(Parser):

    def worker_exec(self, queue_timeout=2, **kwargs):
        while True:
            if self.signal.get('reach_max_num'):
                self.logger.info('downloaded image reached max num, thread %s'
                                 ' exit',
                                 threading.current_thread().name)
                break
            try:
                url = self.in_queue.get(timeout=queue_timeout)
            except queue.Empty:
                if self.signal.get('feeder_exited'):
                    self.logger.info('no more page urls to parse, thread %s'
                                     ' exit',
                                     threading.current_thread().name)
                    break

from bs4 import BeautifulSoup
from six.moves.urllib.parse import urljoin, urlsplit

from icrawler import Crawler, Feeder, Parser, ImageDownloader


class GreedyFeeder(Feeder):

    def feed(self, domains):
        for domain in domains:
            self.output(domain)
        while not self.signal.get('reach_max_num'):
            time.sleep(1)


class GreedyParser(Parser):

    def __init__(self, *args, **kwargs):
        self.pattern = re.compile(
            r'(http|\/\/)(.*)\.(jpg|jpeg|png|bmp|gif|tiff)')
        super(GreedyParser, self).__init__(*args, **kwargs)

    def is_in_domain(self, url, domains):
        for domain in domains:
            if domain in url:
                return True
        return False

    def parse(self, response, domains):
        soup = BeautifulSoup(
            response.content.decode('utf-8', 'ignore'), 'lxml')
        tags = soup.find_all('img', src=True)