Scrapy – 项目管道

无价格的价格验证和删除项目¶

让我们看看下面的假设管道，它调整了 price 不包括增值税的项目的属性 (price_excludes_vat 属性），并删除不包含价格的项目：

from itemadapter import ItemAdapter
from scrapy.exceptions import DropItem
class PricePipeline:
vat_factor = 1.15
def process_item(self, item, spider):
adapter = ItemAdapter(item)
if adapter.get('price'):
if adapter.get('price_excludes_vat'):
adapter['price'] = adapter['price'] * self.vat_factor
return item
else:
raise DropItem(f"Missing price in {item}")

将项目写入JSON文件¶

下面的管道将所有爬取的项目（从所有蜘蛛）存储到一个单独的管道中 items.jl 文件，每行包含一个以JSON格式序列化的项：

import json
from itemadapter import ItemAdapter
class JsonWriterPipeline:
def open_spider(self, spider):
self.file = open('items.jl', 'w')
def close_spider(self, spider):
self.file.close()
def process_item(self, item, spider):
line = json.dumps(ItemAdapter(item).asdict()) + "\n"
self.file.write(line)
return item

将项目写入MongoDB¶

在这个示例中，我们将向 MongoDB 使用 pymongo. 在Scrapy设置中指定MongoDB地址和数据库名称；MongoDB集合以item类命名。

这个例子的要点是演示如何使用 from_crawler() 方法和如何正确清理资源。：：

import pymongo
from itemadapter import ItemAdapter
class MongoPipeline:
collection_name = 'scrapy_items'
def __init__(self, mongo_uri, mongo_db):
self.mongo_uri = mongo_uri
self.mongo_db = mongo_db
@classmethod
def from_crawler(cls, crawler):
return cls(
mongo_uri=crawler.settings.get('MONGO_URI'),
mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')
)
def open_spider(self, spider):
self.client = pymongo.MongoClient(self.mongo_uri)
self.db = self.client[self.mongo_db]
def close_spider(self, spider):
self.client.close()
def process_item(self, item, spider):
self.db[self.collection_name].insert_one(ItemAdapter(item).asdict())
return item

项目截图¶

这个例子演示了如何使用 coroutine syntax 在 process_item() 方法。

此项管道向本地运行的实例发出请求 Splash 呈现项目URL的屏幕截图。下载请求响应后，项目管道将屏幕截图保存到文件中，并将文件名添加到项目中。

import hashlib
from urllib.parse import quote
import scrapy
from itemadapter import ItemAdapter
class ScreenshotPipeline:
"""Pipeline that uses Splash to render screenshot of
    every Scrapy item."""
SPLASH_URL = "http://localhost:8050/render.png?url={}"
async def process_item(self, item, spider):
adapter = ItemAdapter(item)
encoded_item_url = quote(adapter["url"])
screenshot_url = self.SPLASH_URL.format(encoded_item_url)
request = scrapy.Request(screenshot_url)
response = await spider.crawler.engine.download(request, spider)
if response.status != 200:
# Error happened, return item.
return item
# Save screenshot to file, filename will be hash of url.
url = adapter["url"]
url_hash = hashlib.md5(url.encode("utf8")).hexdigest()
filename = f"{url_hash}.png"
with open(filename, "wb") as f:
f.write(response.body)
# Store filename in item.
adapter["screenshot_filename"] = filename
return item

重复筛选器¶

查找重复项并删除已处理的项的筛选器。假设我们的项目有一个唯一的ID，但是我们的spider返回具有相同ID的多个项目：

from itemadapter import ItemAdapter
from scrapy.exceptions import DropItem
class DuplicatesPipeline:
def __init__(self):
self.ids_seen = set()
def process_item(self, item, spider):
adapter = ItemAdapter(item)
if adapter['id'] in self.ids_seen:
raise DropItem(f"Duplicate item found: {item!r}")
else:
self.ids_seen.add(adapter['id'])
return item

注解

jsonWriterPipeline的目的只是介绍如何编写项管道。如果您真的想将所有的爬取项存储到JSON文件中，那么应该使用 Feed exports .

from itemadapter import ItemAdapter
from scrapy.exceptions import DropItem
class PricePipeline:
vat_factor = 1.15
def process_item(self, item, spider):
adapter = ItemAdapter(item)
if adapter.get('price'):
if adapter.get('price_excludes_vat'):
adapter['price'] = adapter['price'] * self.vat_factor
return item
else:
raise DropItem(f"Missing price in {item}")

import json
from itemadapter import ItemAdapter
class JsonWriterPipeline:
def open_spider(self, spider):
self.file = open('items.jl', 'w')
def close_spider(self, spider):
self.file.close()
def process_item(self, item, spider):
line = json.dumps(ItemAdapter(item).asdict()) + "\n"
self.file.write(line)
return item

import pymongo
from itemadapter import ItemAdapter
class MongoPipeline:
collection_name = 'scrapy_items'
def __init__(self, mongo_uri, mongo_db):
self.mongo_uri = mongo_uri
self.mongo_db = mongo_db
@classmethod
def from_crawler(cls, crawler):
return cls(
mongo_uri=crawler.settings.get('MONGO_URI'),
mongo_db=crawler.settings.get('MONGO_DATABASE', 'items')
)
def open_spider(self, spider):
self.client = pymongo.MongoClient(self.mongo_uri)
self.db = self.client[self.mongo_db]
def close_spider(self, spider):
self.client.close()
def process_item(self, item, spider):
self.db[self.collection_name].insert_one(ItemAdapter(item).asdict())
return item

import hashlib
from urllib.parse import quote
import scrapy
from itemadapter import ItemAdapter
class ScreenshotPipeline:
"""Pipeline that uses Splash to render screenshot of
    every Scrapy item."""
SPLASH_URL = "http://localhost:8050/render.png?url={}"
async def process_item(self, item, spider):
adapter = ItemAdapter(item)
encoded_item_url = quote(adapter["url"])
screenshot_url = self.SPLASH_URL.format(encoded_item_url)
request = scrapy.Request(screenshot_url)
response = await spider.crawler.engine.download(request, spider)
if response.status != 200:
# Error happened, return item.
return item
# Save screenshot to file, filename will be hash of url.
url = adapter["url"]
url_hash = hashlib.md5(url.encode("utf8")).hexdigest()
filename = f"{url_hash}.png"
with open(filename, "wb") as f:
f.write(response.body)
# Store filename in item.
adapter["screenshot_filename"] = filename
return item

from itemadapter import ItemAdapter
from scrapy.exceptions import DropItem
class DuplicatesPipeline:
def __init__(self):
self.ids_seen = set()
def process_item(self, item, spider):
adapter = ItemAdapter(item)
if adapter['id'] in self.ids_seen:
raise DropItem(f"Duplicate item found: {item!r}")
else:
self.ids_seen.add(adapter['id'])
return item

ITEM_PIPELINES = {
'myproject.pipelines.PricePipeline': 300,
'myproject.pipelines.JsonWriterPipeline': 800,
}