From 750b6ccb1927682674cc2a3bf38c8088c0b1415f Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:26:09 +0800 Subject: [PATCH 1/7] =?UTF-8?q?=E6=96=B0=E5=BB=BA=203=E7=8F=AD=5F=E9=99=B6?= =?UTF-8?q?=E5=86=B6=5F=E7=AC=AC=E5=8D=81=E4=BA=8C=E5=91=A8?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../.keep" | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/.keep" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/.keep" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/.keep" new file mode 100644 index 00000000..e69de29b -- Gitee From 354b4c577a714a6c7362c6eec33807686b809289 Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:27:15 +0800 Subject: [PATCH 2/7] =?UTF-8?q?=E6=96=B0=E5=BB=BA=20=E7=AC=AC=E5=8D=81?= =?UTF-8?q?=E4=BA=8C=E5=91=A8=5F=E7=AC=AC=E4=B8=80=E8=8A=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../.keep" | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/.keep" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/.keep" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/.keep" new file mode 100644 index 00000000..e69de29b -- Gitee From 50f168cf1005c9aef00e67e72af98ed3596deb1a Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:27:27 +0800 Subject: [PATCH 3/7] =?UTF-8?q?=E6=96=B0=E5=BB=BA=20=E7=AC=AC=E5=8D=81?= =?UTF-8?q?=E4=BA=8C=E5=91=A8=5F=E7=AC=AC=E4=BA=8C=E8=8A=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../.keep" | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/.keep" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/.keep" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/.keep" new file mode 100644 index 00000000..e69de29b -- Gitee From a37effd110dd021c032a26b79dcb2f1320fba781 Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:27:39 +0800 Subject: [PATCH 4/7] =?UTF-8?q?=E6=96=B0=E5=BB=BA=20=E7=AC=AC=E5=8D=81?= =?UTF-8?q?=E4=BA=8C=E5=91=A8=5F=E7=AC=AC=E4=B8=89=E8=8A=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../.keep" | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/.keep" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/.keep" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/.keep" new file mode 100644 index 00000000..e69de29b -- Gitee From 9f47cffc39a3b1eeb2aa4bf172fb18fb48cb86d7 Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:32:25 +0800 Subject: [PATCH 5/7] =?UTF-8?q?=E7=AC=AC=E5=8D=81=E4=BA=8C=E5=91=A8=5F?= =?UTF-8?q?=E7=AC=AC=E4=B8=80=E8=8A=82=20=E7=AC=AC=E5=8D=81=E4=BA=8C?= =?UTF-8?q?=E5=91=A8=5F=E7=AC=AC=E4=B8=80=E8=8A=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../jd_producer.py" | 28 +++ .../jd_search.py" | 62 ++++++ .../middlewares.py" | 185 ++++++++++++++++++ .../settings.py" | 130 ++++++++++++ 4 files changed, 405 insertions(+) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_producer.py" create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_search.py" create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py" create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_producer.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_producer.py" new file mode 100644 index 00000000..68d751f4 --- /dev/null +++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_producer.py" @@ -0,0 +1,28 @@ +import redis +import time +import json + +redis_con = redis.Redis(host='localhost', port=6379, db=5) + +def search_producer(): + for keyword in ["鼠标", "键盘", "显卡", "耳机"]: + for page_num in range(1, 11): + url = f"https://search.jd.com/Search?keyword={keyword}&page={page_num}" + mata = { + "sta_date": time.strftime("%Y-%m-%d"), + "keyword": keyword, + "page_num": page_num + } + + + task = json.dumps({ + "url": url, + "body": '', + "method": "GET", + "meta": meta + + }) + redis_con.lpush("jd_search:start_urls", task ) + +if __name__ == "__main__": + search_producer() \ No newline at end of file diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_search.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_search.py" new file mode 100644 index 00000000..5cb73a01 --- /dev/null +++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/jd_search.py" @@ -0,0 +1,62 @@ +import scrapy +import json +import time +from bs4 import BeautifulSoup +from jd_crawler_scrapy.jd_crawler_scrapy.items import JdCrawlerScrapyItem +from scrapy.exceptions import CloseSpider +from scrapy_redis.spiders import RedisSpider + +class JdSearch(RedisSpider): + name = "jd_search" + redis_key = f"{name}:start_urls" + + def make_request_from_date(self, data): + task = json.loads(data.decode("utf-8")) + return scrapy.http.FormRequest(url=task['url'], + formdata=json.loads(task['body']) if task['body'] else '', + method=task['method'], + meta=task['meta'], + dont_filter=False, + callback=self.parse_search(), + errback=self.process_error + ) + + def parse_search(self, response): + print(response) + soup = BeautifulSoup(response.text, "lxml") + item_array = soup.select("ul[class='gl-warp clearfix'] li[class='gl-item']") + for item in item_array: + try: + sku_id = item.attrs["date-sku"] + img = item.select("img[data-img='1']") + price = item.select("div[class='p-price']") + title = item.select("div[class='p-name p-name-type-2']") + shop = item.select("div[class='p-shop']") + icons = item.select("div[class='p-icons']") + + img = img[0].attrs['data-lazy-img'] if img else "" + price = price[0].strong.i.text if price else "" + title = title[0].text.strip() if title else "" + shop = shop[0].span.a.attrs['title'] if shop[0].text.strip() else "" + icons = json.dumps([tag_ele.text for tag_ele in icons[0].select("i")]) if icons else '[]' + + item = JdCrawlerScrapyItem() + + item["sku_id"] = sku_id + item["img"] = img + item["price"] = price + item["title"] = title + item["shop"] = shop + item["icons"] = icons + item["sta_date"] = response.meta["sta_date"] + item["keyword"] = response.meta["keyword"] + yield item + except Exception as e: + print(e.args) + def process_error(self, failure): + print(failure) + if "身份已过期" in str(failure.value): + raise CloseSpider + #记录异常 + #发送通知 + #重做任务 \ No newline at end of file diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py" new file mode 100644 index 00000000..081dafab --- /dev/null +++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/middlewares.py" @@ -0,0 +1,185 @@ +# Define here the models for your spider middleware +# +# See documentation in: +# https://docs.scrapy.org/en/latest/topics/spider-middleware.html + +from scrapy.utils.response import response_status_message +from scrapy.dupefilters import RFPDupeFilter +from scrapy import signals +from scrapy.downloadermiddlewares.retry import RetryMiddleware +from itemadapter import is_item, ItemAdapter +from w3lib.url import canonicalize_url +from scrapy.utils.python import to_bytes +import random + +import hashlib +import weakref + +_fingerprint_cache = weakref.WeakKeyDictionary() + +class JdCrawlerScrapySpiderMiddleware: + # Not all methods need to be defined. If a method is not defined, + # scrapy acts as if the spider middleware does not modify the + # passed objects. + + @classmethod + def from_crawler(cls, crawler): + # This method is used by Scrapy to create your spiders. + s = cls() + crawler.signals.connect(s.spider_opened, signal=signals.spider_opened) + return s + + def process_spider_input(self, response, spider): + # Called for each response that goes through the spider + # middleware and into the spider. + + # Should return None or raise an exception. + return None + + def process_spider_output(self, response, result, spider): + # Called with the results returned from the Spider, after + # it has processed the response. + + # Must return an iterable of Request, or item objects. + for i in result: + yield i + + def process_spider_exception(self, response, exception, spider): + # Called when a spider or process_spider_input() method + # (from other spider middleware) raises an exception. + + # Should return either None or an iterable of Request or item objects. + pass + + def process_start_requests(self, start_requests, spider): + # Called with the start requests of the spider, and works + # similarly to the process_spider_output() method, except + # that it doesn’t have a response associated. + + # Must return only requests (not items). + for r in start_requests: + yield r + + def spider_opened(self, spider): + spider.logger.info('Spider opened: %s' % spider.name) + + +class JdCrawlerScrapyDownloaderMiddleware: + # Not all methods need to be defined. If a method is not defined, + # scrapy acts as if the downloader middleware does not modify the + # passed objects. + + @classmethod + def from_crawler(cls, crawler): + # This method is used by Scrapy to create your spiders. + s = cls() + crawler.signals.connect(s.spider_opened, signal=signals.spider_opened) + return s + + def process_request(self, request, spider): + # Called for each request that goes through the downloader + # middleware. + + # Must either: + # - return None: continue processing this request + # - or return a Response object + # - or return a Request object + # - or raise IgnoreRequest: process_exception() methods of + # installed downloader middleware will be called + return None + + def process_response(self, request, response, spider): + # Called with the response returned from the downloader. + + # Must either; + # - return a Response object + # - return a Request object + # - or raise IgnoreRequest + return response + + def process_exception(self, request, exception, spider): + # Called when a download handler or a process_request() + # (from other downloader middleware) raises an exception. + + # Must either: + # - return None: continue processing this exception + # - return a Response object: stops process_exception() chain + # - return a Request object: stops process_exception() chain + pass + + def spider_opened(self, spider): + spider.logger.info('Spider opened: %s' % spider.name) + +class CookieMiddleware: + def process_request(self, request, spider): + request.headers['cookie'] = "__jdu=1614325433253970893691; shshshfpa=625e93d5-fd42-706f-f2d3-ab101d15ab0f-1614325435; shshshfpb=gaY1DAmAE0ZGoq6pKTzwp1g%3D%3D; qrsc=3; unpl=V2_ZzNtbRcDRkF2D0YHch1dBGIARVkSUkURIFtEAHgbC1VnBEcOclRCFnUUR1ZnGV8UZAMZX0NcQBBFCEdkexhdBGYCEFpBU3MXcgkaH0spXwVXAxNtQlBDEHcLQlF5G18BZQsUXEtfQRJ9CHZkfClsNWYzE21DZwh7dEVGU3scXgZjBhBfQVNBHXMJT1x5HlQFVwIiXg%3d%3d; __jdv=76161171|hao.360.com|t_1000003625_360mz|tuiguang|de4e261b850042f5a475db3e23fa16db|1615555825008; areaId=17; ipLoc-djd=17-1381-50713-0; PCSYCityID=CN_420000_420100_420115; shshshfp=2ef78080f2acedbd438b03639d0c23f9; shshshsID=c25819d14bbc4c305d9dde6736271c1d_2_1615555832536; __jda=122270672.1614325433253970893691.1614325433.1614491521.1615555825.3; __jdb=122270672.2.1614325433253970893691|3.1615555825; __jdc=122270672; rkv=1.0; 3AB9D23F7A4B3C9B=NG6VDTXK6GA3XU67UGNLBN42IXRZPG6VW5H3OO7EGHU7HFONTMVI6QYEAK75CUFUTHZPEZ2JQFZE3W2YCJHHLF5BN4" + + def process_response(self, request, response,spider): + """ + 根据response返回的内容判断cookie身份是否已过期 + dangqiam + :param request: + :param response: + :param spider: + :return: + """ + if "身份过期" in response.text: + raise Exception("当前cookie身份已过期") + + def process_exception(self, request, exception, spider): + # 如果异常是cookie池空了，可以在这里完成cookie池的补充 + # + if isinstance(exception, ImportError): + retry_times = request.meta.get('retry_times', 1) + request.meta['retru_times'] = retry_times -1 + return request + +class UAMiddleware: + def process_request(self, request, spider): + """ + 在正式请求前为当前请求添加headers + :param request: + :param spider: + :return: + """ + request.headers["user-agent"] = "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Mobile Safari/537.36" + + +class MyRetryMiddleware(RetryMiddleware): + """ + 解决对方服务器返回正常状态码200，但是根据IP需要进行验证码验证的情况 + 通过换IP可以解决验证码，那么应该可以重试 + + """ + def process_response(self, request, response, spider): + if request.meta.get('dont_retry', False): + return response + if "验证码" in response.text: + raise Exception("当前cookie身份已过期") + #reason = response_status_message(response.status) + # return self._retry(request, reason, spider) or response + # return response + +class MyRFPDupeFilter(RFPDupeFilter): + """ + 过滤器是在到达下载之前九生成了过滤指纹，如果我们的下载器中间件报错，那么过滤指纹仍然生效，但是没有实际请求， + 所以我们可以通过一些特殊参数来进行自定义过滤规则 + + + """ + def request_fingerprint(self, request, include_headers=None, keep_gragments=False): + cache = _fingerprint_cache.setdefault(request, {}) + cache_key = (include_headers, keep_gragments) + if cache_key not in cache: + fp = hashlib.sha1() + fp.update(to_bytes(request.method)) + fp.update(to_bytes(canonicalize_url(request.url, keep_fragments=keep_gragments))) + fp.update(request.body or b'') + fp.update(request.meta.get("batch_no", "").encode("utf-8")) + cache[cache_key] = fp.hexdigest() + return cache[cache_key] + + + + + diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py" new file mode 100644 index 00000000..dec3ba29 --- /dev/null +++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\200\350\212\202/settings.py" @@ -0,0 +1,130 @@ +# Scrapy settings for jd_crawler_scrapy project +# +# For simplicity, this file contains only settings considered important or +# commonly used. You can find more settings consulting the documentation: +# +# https://docs.scrapy.org/en/latest/topics/settings.html +# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +# https://docs.scrapy.org/en/latest/topics/spider-middleware.html + +BOT_NAME = 'jd_crawler_scrapy' + +SPIDER_MODULES = ['jd_crawler_scrapy.spiders'] +NEWSPIDER_MODULE = 'jd_crawler_scrapy.spiders' + + +# Crawl responsibly by identifying yourself (and your website) on the user-agent +#USER_AGENT = 'jd_crawler_scrapy (+http://www.yourdomain.com)' + +# Obey robots.txt rules +ROBOTSTXT_OBEY = False + +#enable redirect +REDIRECT_ENABLE = False + +#retry +RETRY_ENABLE = False +RETRY_HTTP_CODES = [500, 502, 503, 408, 429] + +# Configure maximum concurrent requests performed by Scrapy (default: 16) 请求限制 +CONCURRENT_REQUESTS = 1 + +# Configure a delay for requests for the same website (default: 0) +# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay +# See also autothrottle settings and docs +DOWNLOAD_DELAY = 3 +# The download delay setting will honor only one of: +#CONCURRENT_REQUESTS_PER_DOMAIN = 16 +#CONCURRENT_REQUESTS_PER_IP = 16 + +# Disable cookies (enabled by default) +#COOKIES_ENABLED = False + +# Disable Telnet Console (enabled by default) +#TELNETCONSOLE_ENABLED = False + +# Override the default request headers: +#DEFAULT_REQUEST_HEADERS = { +# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', +# 'Accept-Language': 'en', +#} + +# Enable or disable spider middlewares +# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html +#SPIDER_MIDDLEWARES = { +# 'jd_crawler_scrapy.middlewares.JdCrawlerScrapySpiderMiddleware': 543, +#} + +# Enable or disable downloader middlewares +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html +DOWNLOADER_MIDDLEWARES = { +# 'jd_crawler_scrapy.middlewares.JdCrawlerScrapyDownloaderMiddleware': 543, + 'jd_crawler_scrapy.middlewares.UAMiddleware': 100, + 'jd_crawler_scrapy.middlewares.MyRetryMiddleware': 200, + 'jd_crawler_scrapy.middlewares.CookieMiddleware': 150, +} + +# Enable or disable extensions +# See https://docs.scrapy.org/en/latest/topics/extensions.html +#EXTENSIONS = { +# 'scrapy.extensions.telnet.TelnetConsole': None, +#} + +# Configure item pipelines +# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html +ITEM_PIPELINES = { + 'jd_crawler_scrapy.pipelines.JdCrawlerScrapyPipeline': 300, +} + +# Enable and configure the AutoThrottle extension (disabled by default) +# See https://docs.scrapy.org/en/latest/topics/autothrottle.html +#AUTOTHROTTLE_ENABLED = True +# The initial download delay +#AUTOTHROTTLE_START_DELAY = 5 +# The maximum download delay to be set in case of high latencies +#AUTOTHROTTLE_MAX_DELAY = 60 +# The average number of requests Scrapy should be sending in parallel to +# each remote server +#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0 +# Enable showing throttling stats for every response received: +#AUTOTHROTTLE_DEBUG = False + +# Enable and configure HTTP caching (disabled by default) +# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings +#HTTPCACHE_ENABLED = True +#HTTPCACHE_EXPIRATION_SECS = 0 +#HTTPCACHE_DIR = 'httpcache' +#HTTPCACHE_IGNORE_HTTP_CODES = [] +#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage' + + +#MYSQL_CONF +MYSQL_CONF = { + "host": "127.0.0.1", + "user": "root", + "password": "lmc.123", + "db": "tunan_class3" +} + + +#log +#LOG_FILE = "F:\log\jd_search.log" +LOG_LEVEL= "DEBUG" + +#dup +DUOEFILTER_CLASS = "jd_crawler_scrapy.middleware.MyRFPDupefilter" + + + +# Scrapy-redis settings +SCHEDULER = 'scrapy_redis.scheduler.Scheduler' +SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue' +DUOEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter" +SCHEDULER_PERSIST = True + + +# Redis settings +REDIS_HOST = 'localhost' +REDIS_PORT = 6379 +#redis 参数配置 +REDIS_PARAMS = {"db": 5} \ No newline at end of file -- Gitee From 937fc9920870a4539dcb11403315decd0ea1be1b Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:33:07 +0800 Subject: [PATCH 6/7] =?UTF-8?q?=E7=AC=AC=E5=8D=81=E4=BA=8C=E5=91=A8=5F?= =?UTF-8?q?=E7=AC=AC=E4=BA=8C=E8=8A=82=20=E7=AC=AC=E5=8D=81=E4=BA=8C?= =?UTF-8?q?=E5=91=A8=5F=E7=AC=AC=E4=BA=8C=E8=8A=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../jd_serach.py" | 31 +++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/jd_serach.py" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/jd_serach.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/jd_serach.py" new file mode 100644 index 00000000..c436365e --- /dev/null +++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\272\214\350\212\202/jd_serach.py" @@ -0,0 +1,31 @@ +from selenium import webdriver +from jd_crawler.jd_parser import search +import time + +driver_path = r"F:\driver\chromedriver.exe" + +chrome_options = webdriver.ChromeOptions() +chrome_options.add_argument("disable-blink-features=AutomationControlled") +browser = webdriver.Chrome(executable_path=driver_path, chrome_options=chrome_options) + + +class whole: + def sim_search(keyword, url): + browser.get(url) + search_input = browser.find_element_by_css_selector('input[aria-label="搜索"]') + search_input.send_keys("鼠标") + search_button = browser.find_element_by_css_selector('button[aria-label="搜索"]') + search_button.click() + + + + def main(keyword, url): + whole.sim_search(keyword, url) + time.sleep(3) + item_array = item_array = search.parse_jd_item(browser.page_source) + print(item_array) + browser.close() + +if __name__ == "__main__": + jd_url = "https://www.jd.com/" + whole.main("鼠标", jd_url) -- Gitee From be7abcea141b90850ee953cb3d629dfb76770090 Mon Sep 17 00:00:00 2001 From: doepy <8428487+doepy@user.noreply.gitee.com> Date: Sun, 21 Mar 2021 22:33:33 +0800 Subject: [PATCH 7/7] =?UTF-8?q?=E7=AC=AC=E5=8D=81=E4=BA=8C=E5=91=A8=5F?= =?UTF-8?q?=E7=AC=AC=E4=B8=89=E8=8A=82=20=E7=AC=AC=E5=8D=81=E4=BA=8C?= =?UTF-8?q?=E5=91=A8=5F=E7=AC=AC=E4=B8=89=E8=8A=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../jd_search.py" | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 "\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/jd_search.py" diff --git "a/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/jd_search.py" "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/jd_search.py" new file mode 100644 index 00000000..f9580833 --- /dev/null +++ "b/\347\254\254\344\272\214\346\234\237\350\256\255\347\273\203\350\220\245/3\347\217\255/3\347\217\255_\351\231\266\345\206\266/3\347\217\255_\351\231\266\345\206\266_\347\254\254\345\215\201\344\272\214\345\221\250/\347\254\254\345\215\201\344\272\214\345\221\250_\347\254\254\344\270\211\350\212\202/jd_search.py" @@ -0,0 +1,59 @@ +from selenium import webdriver +from selenium.webdriver import ActionChains +from selenium.webdriver.common.keys import Keys +from jd_crawler.jd_parser import search +import time + +driver_path = r"F:\driver\chromedriver.exe" + + +class JdSearch: + def __init__(self, proxy=None, ua=None, headless=False, user_dir=None): + chrome_options = webdriver.ChromeOptions() + chrome_options.add_argument("disable-blink-features=AutomationControlled") + if proxy: + chrome_options.add_argument(f"--proxy-server={proxy}") + if ua: + chrome_options.add_argument(f"--user-agent={ua}") + if headless: + chrome_options.add_argument("--headless") + if user_dir: + chrome_options.add_argument(f"--user-data-dir={user_dir}") + self.browser = webdriver.Chrome(executable_path=driver_path, chrome_options=chrome_options) + self.browser.maximize_window() + self.browser.set_window_size(width=1660, height=960) + self.browser.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", { + "source": """ + Object.defineProperty(navigator, 'webdriver',{ + get:()=> 'my_webdriver' + }) + """ + }) + + def sim_search(self, keyword, url): + self.browser.get(url) + search_input = self.browser.find_element_by_css_selector('input[aria-label="搜索"]') + search_input.send_keys("鼠标") + search_button = self.browser.find_element_by_css_selector('button[aria-label="搜索"]') + search_button.click() + + + + def main(self, keyword, url): + self.sim_search(keyword, url) + time.sleep(3) + self.browser.execute_script("window.open('http://baidu.com')") + self.browser.switch_to.window(self.browser.window_handles[-1]) + ac = ActionChains(self.browser) + ac.send_keys(Keys.ENTER).perform() + item_array = search.parse_jd_item(self.browser.page_source) + print(item_array) + self.browser.close() + +if __name__ == "__main__": + jd_url = "https://www.jd.com/" + proxy = "127.0.0.1:8888" + ua = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36" + user_dir = r"D:\driver\tmp" + jd_search = JdSearch() + jd_search.main("鼠标", jd_url) -- Gitee