scrapy选择器的用法
//selector可以加可以不加
response.selector.xpath("//title/text()").extract_first()
response.selector.css("title::text").extract_first()
response.xpath("//title/text()").extract_first()
response.xpath("//div[@id='images']").xpath("//img/@src").extract()[0]
response.css('a::text').re('Name\:(.*)')---需要特殊处理的数据后面可以加re模块
response.xpath("//a/text()").re('Name\:(.*)')--这个后面对象变了,不能再加extract()方法了
spiders的用法
完成爬虫的逻辑url
解析网页数据parse
1.初始start_urls→解析parse→scrapy.Request(url,callback=parse)
item
url继续给下载器
2.name---唯一标识爬虫
3.allowed_domains---允许爬取列表
4.start_urls---从这里开始,可以构造列表,一个一个请求(遍历),get形式的请求
5.custom_settings---字典形式的写法(参考headers设置)可以覆盖项目settings---可以吧请求头写在myspider中
6.crawler---
7.settings---
8.from_crawler----可以拿到全局配置
9.start_requests()----利用改写start_requests()方法,使第一次请求用post请求
def start_requests(self):
yield scrapy.Request(url='http://httpbin.org/post',method='post',callback=self.parse_post)
def parse_post(self,response):
print('OK',response.status)
10.make_requests_from_url--改变默认回调函数,将回调函数改写,,如果先写start_requests函数就不会在调用此函数
def make_requests_from_url(self,url):
yield scrapy.Request(url=url,callback=self.parse_index)
def parse_index(self,response):
print('OK',response.status)
11.parse默认回调函数--item 可迭代对象,request(加到下载队列)
12.log日志文件--info --debug
self.logger.info(response.status)
13.closed--myspider关闭时调用
item Pipeline的用法
数据清洗
重复检查
存储到数据库
1.process_item---item会自动传给它
2.open_spider---spider开启的时候调用
3.close_spider--spider关闭的时候调用
4.from-crawler----类方法,获取项目中的setting
from scrapy.exceptions import DropItem
标准写法:
class PricePipeline(object):
vat_factor = 1.15
def process_item(self, item, spider):
if item.get('price'):
if item.get('price_excludes_vat'):
item['price'] = item['price'] * self.vat_factor
return item
else:
raise DropItem("Missing price in %s" % item)
写到json:
import json
class JsonWriterPipeline(object):
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(dict(item)) + "\n"
self.file.write(line)
return item
存储到MongoDB:
import pymongo
class MongoPipeline(object):
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(dict(item))
return item
请求网页,保存图片
import scrapy
import hashlib
from urllib.parse import quote
class ScreenshotPipeline(object):
"""Pipeline that uses Splash to render screenshot of
every Scrapy item."""
SPLASH_URL = "http://localhost:8050/render.png?url={}"
def process_item(self, item, spider):
encoded_item_url = quote(item["url"])
screenshot_url = self.SPLASH_URL.format(encoded_item_url)
request = scrapy.Request(screenshot_url)
dfd = spider.crawler.engine.download(request, spider)
dfd.addBoth(self.return_item, item)
return dfd
def return_item(self, response, item):
if response.status != 200:
# Error happened, return item.
return item
# Save screenshot to file, filename will be hash of url.
url = item["url"]
url_hash = hashlib.md5(url.encode("utf8")).hexdigest()
filename = "{}.png".format(url_hash)
with open(filename, "wb") as f:
f.write(response.body)
# Store filename in item.
item["screenshot_filename"] = filename
return item
去重操作:
from scrapy.exceptions import DropItem
class DuplicatesPipeline(object):
def __init__(self):
self.ids_seen = set()
def process_item(self, item, spider):
if item['id'] in self.ids_seen:
raise DropItem("Duplicate item found: %s" % item)
else:
self.ids_seen.add(item['id'])
return item
使用item pipeline:
ITEM_PIPELINES = {
'myproject.pipelines.PricePipeline': 300,
'myproject.pipelines.JsonWriterPipeline': 800,
}
