How to use icrawler - 10 common examples

if len(tmp) > 1 and tmp[-1] not in [
                        'html', 'shtml', 'shtm', 'php', 'jsp', 'asp'
                ]:
                    continue
                # discard urls such as 'javascript:void(0)'
                elif href.find('javascript', 0, 10) == 0:
                    continue
                # discard urls such as 'android-app://xxxxxxxxx'
                elif urlsplit(href).scheme not in ['http', 'https', 'ftp']:
                    continue
                # urls of the same domain
                elif self.is_in_domain(href, domains):
                    yield href


class GreedyImageCrawler(Crawler):

    def __init__(self,
                 feeder_cls=GreedyFeeder,
                 parser_cls=GreedyParser,
                 downloader_cls=ImageDownloader,
                 *args,
                 **kwargs):
        super(GreedyImageCrawler, self).__init__(
            feeder_cls, parser_cls, downloader_cls, *args, **kwargs)

    def crawl(self,
              domains,
              max_num=0,
              min_size=None,
              max_size=None,
              file_idx_offset=0):

from icrawler.storage import BaseStorage
from io import BytesIO


class GoogleStorage(BaseStorage):
    """Google Storage backend.

    The id is filename and data is stored as text files or binary files.
    The root_dir is the bucket address such as gs:///.
    """

    def __init__(self, root_dir):
        try:
            from google.cloud import storage
        except ImportError:
            print('GoogleStorage backend requires the package '
                  '"google-cloud-storage", execute '
                  '"pip install google-cloud-storage" to install it.')

        self.client = storage.Client()
        bucket_str = root_dir[5:].split('/')[0]

def set_storage(self, storage):
        """Set storage backend for downloader

        For full list of storage backend supported, please see :mod:`storage`.

        Args:
            storage (dict or BaseStorage): storage backend configuration or instance

        """
        if isinstance(storage, BaseStorage):
            self.storage = storage
        elif isinstance(storage, dict):
            if 'backend' not in storage and 'root_dir' in storage:
                storage['backend'] = 'FileSystem'
            try:
                backend_cls = getattr(storage_package, storage['backend'])
            except AttributeError:
                try:
                    backend_cls = import_module(storage['backend'])
                except ImportError:
                    self.logger.error('cannot find backend module %s',
                                      storage['backend'])
                    sys.exit()
            kwargs = storage.copy()
            del kwargs['backend']
            self.storage = backend_cls(**kwargs)

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
            }