Commit ccae929b authored by jackfrued's avatar jackfrued

更新了爬虫部分的代码

parent 0f19b236
## Scrapy的应用(01) ## Scrapy爬虫框架的应用
### Scrapy概述 ### Scrapy概述
...@@ -101,6 +101,11 @@ $ ...@@ -101,6 +101,11 @@ $
2. 在spiders文件夹中编写自己的爬虫。 2. 在spiders文件夹中编写自己的爬虫。
```Shell
(venv) $ scrapy genspider movie movie.douban.com --template=crawl
```
```Python ```Python
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
...@@ -287,5 +292,77 @@ $ ...@@ -287,5 +292,77 @@ $
HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage' HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
``` ```
### 补充说明
#### XPath语法
1. XPath路径表达式:XPath使用路径表达式来选取XML文档中的节点或者节点集。
2. XPath节点:元素、属性、文本、命名空间、处理指令、注释、根节点。
3. XPath语法。(注:下面的例子来自于[菜鸟教程](http://www.runoob.com/)网站的[XPath教程](http://www.runoob.com/xpath/xpath-syntax.html)。)
XML文件。
```XML
<?xml version="1.0" encoding="UTF-8"?>
<bookstore>
<book>
<title lang="eng">Harry Potter</title>
<price>29.99</price>
</book>
<book>
<title lang="eng">Learning XML</title>
<price>39.95</price>
</book>
</bookstore>
```
XPath语法。
| 路径表达式 | 结果 |
| --------------- | ------------------------------------------------------------ |
| bookstore | 选取 bookstore 元素的所有子节点。 |
| /bookstore | 选取根元素 bookstore。注释:假如路径起始于正斜杠( / ),则此路径始终代表到某元素的绝对路径! |
| bookstore/book | 选取属于 bookstore 的子元素的所有 book 元素。 |
| //book | 选取所有 book 子元素,而不管它们在文档中的位置。 |
| bookstore//book | 选择属于 bookstore 元素的后代的所有 book 元素,而不管它们位于 bookstore 之下的什么位置。 |
| //@lang | 选取名为 lang 的所有属性。 |
XPath谓词。
| 路径表达式 | 结果 |
| ---------------------------------- | ------------------------------------------------------------ |
| /bookstore/book[1] | 选取属于 bookstore 子元素的第一个 book 元素。 |
| /bookstore/book[last()] | 选取属于 bookstore 子元素的最后一个 book 元素。 |
| /bookstore/book[last()-1] | 选取属于 bookstore 子元素的倒数第二个 book 元素。 |
| /bookstore/book[position()<3] | 选取最前面的两个属于 bookstore 元素的子元素的 book 元素。 |
| //title[@lang] | 选取所有拥有名为 lang 的属性的 title 元素。 |
| //title[@lang='eng'] | 选取所有 title 元素,且这些元素拥有值为 eng 的 lang 属性。 |
| /bookstore/book[price>35.00] | 选取 bookstore 元素的所有 book 元素,且其中的 price 元素的值须大于 35.00。 |
| /bookstore/book[price>35.00]/title | 选取 bookstore 元素中的 book 元素的所有 title 元素,且其中的 price 元素的值须大于 35.00。 |
通配符用法。
| 路径表达式 | 结果 |
| ------------ | --------------------------------- |
| /bookstore/* | 选取 bookstore 元素的所有子元素。 |
| //* | 选取文档中的所有元素。 |
| //title[@*] | 选取所有带有属性的 title 元素。 |
选取多个路径。
| 路径表达式 | 结果 |
| -------------------------------- | ------------------------------------------------------------ |
| //book/title \| //book/price | 选取 book 元素的所有 title 和 price 元素。 |
| //title \| //price | 选取文档中的所有 title 和 price 元素。 |
| /bookstore/book/title \| //price | 选取属于 bookstore 元素的 book 元素的所有 title 元素,以及文档中所有的 price 元素。 |
#### 在Chrome浏览器中查看元素XPath语法
![](./res/douban-xpath.png)
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class DoubanItem(scrapy.Item):
name = scrapy.Field()
year = scrapy.Field()
score = scrapy.Field()
director = scrapy.Field()
classification = scrapy.Field()
actor = scrapy.Field()
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class DoubanSpiderMiddleware(object):
# 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, dict 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 Response, dict
# 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 DoubanDownloaderMiddleware(object):
# 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)
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import pymongo
from scrapy.exceptions import DropItem
from scrapy.conf import settings
from scrapy import log
class DoubanPipeline(object):
def __init__(self):
connection = pymongo.MongoClient(settings['MONGODB_SERVER'], settings['MONGODB_PORT'])
db = connection[settings['MONGODB_DB']]
self.collection = db[settings['MONGODB_COLLECTION']]
def process_item(self, item, spider):
#Remove invalid data
valid = True
for data in item:
if not data:
valid = False
raise DropItem("Missing %s of blogpost from %s" %(data, item['url']))
if valid:
#Insert data into database
new_moive=[{
"name":item['name'][0],
"year":item['year'][0],
"score":item['score'],
"director":item['director'],
"classification":item['classification'],
"actor":item['actor']
}]
self.collection.insert(new_moive)
log.msg("Item wrote to MongoDB database %s/%s" %
(settings['MONGODB_DB'], settings['MONGODB_COLLECTION']),
level=log.DEBUG, spider=spider)
return item
# -*- coding: utf-8 -*-
# Scrapy settings for douban project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'douban'
SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.54 Safari/536.5'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 3
RANDOMIZE_DOWNLOAD_DELAY = True
# 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 = True
MONGODB_SERVER = '120.77.222.217'
MONGODB_PORT = 27017
MONGODB_DB = 'douban'
MONGODB_COLLECTION = 'movie'
# 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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'douban.middlewares.DoubanSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'douban.middlewares.DoubanDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'douban.pipelines.DoubanPipeline': 400,
}
LOG_LEVEL = 'DEBUG'
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.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://doc.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'
# This package will contain the spiders of your Scrapy project
#
# Please refer to the documentation for information on how to create and manage
# your spiders.
# -*- coding: utf-8 -*-
import scrapy
from scrapy.selector import Selector
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from douban.items import DoubanItem
class MovieSpider(CrawlSpider):
name = 'movie'
allowed_domains = ['movie.douban.com']
start_urls = ['https://movie.douban.com/top250']
rules = (
Rule(LinkExtractor(allow=(r'https://movie.douban.com/top250\?start=\d+.*'))),
Rule(LinkExtractor(allow=(r'https://movie.douban.com/subject/\d+')), callback='parse_item'),
)
def parse_item(self, response):
sel = Selector(response)
item = DoubanItem()
item['name']=sel.xpath('//*[@id="content"]/h1/span[1]/text()').extract()
item['year']=sel.xpath('//*[@id="content"]/h1/span[2]/text()').re(r'\((\d+)\)')
item['score']=sel.xpath('//*[@id="interest_sectl"]/div/p[1]/strong/text()').extract()
item['director']=sel.xpath('//*[@id="info"]/span[1]/a/text()').extract()
item['classification']= sel.xpath('//span[@property="v:genre"]/text()').extract()
item['actor']= sel.xpath('//*[@id="info"]/span[3]/a[1]/text()').extract()
#i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
#i['name'] = response.xpath('//div[@id="name"]').extract()
#i['description'] = response.xpath('//div[@id="description"]').extract()
return item
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.io/en/latest/deploy.html
[settings]
default = douban.settings
[deploy]
#url = http://localhost:6800/
project = douban
import pymongo
# BSON - Binary JSON - dict
def main():
# client = pymongo.MongoClient('mongodb://120.77.222.217:27017')
client = pymongo.MongoClient(host='120.77.222.217', port=27017)
db = client.zhihu
pages_cache = db.webpages
"""
pages_cache.insert_many([
{'_id': 1, 'url': 'http://www.baidu.com', 'content': 'shit'},
{'_id': 2, 'url': 'http://www.qq.com', 'content': 'another shit'},
{'_id': 3, 'url': 'http://www.qfedu.com', 'content': 'biggest shit'}
])
print(pages_cache.update({'_id': 5}, {'$set': {'content': 'hello, world!'}}, upsert=True))
# page_id = pages_cache.insert_one({'url': 'http://www.baidu.com', 'content': '<html></html>'})
# print(page_id.inserted_id)
# print(pages_cache.remove({'url': 'http://www.baidu.com'}))
print(pages_cache.find().count())
for doc in pages_cache.find().sort('_id'):
print(doc)
"""
pages_cache.insert_one({
'url': 'http://www.baidu.com',
'content': 'bull shit!',
'owner': {
'name': 'Lee Yanhong',
'age': 50,
'idcard': '110220196804091203'
}
})
if __name__ == '__main__':
main()
import requests
from bs4 import BeautifulSoup
def main():
resp = requests.get('https://github.com/login')
if resp.status_code != 200:
return
cookies = resp.cookies.get_dict()
print(cookies)
soup = BeautifulSoup(resp.text, 'lxml')
utf8_value = \
soup.select_one('form input[name=utf8]').attrs['value']
authenticity_token_value = \
soup.select_one('form input[name=authenticity_token]').attrs['value']
data = {
'utf8': utf8_value,
'authenticity_token': authenticity_token_value,
'login': 'jackfrued@gmail.com',
'password': 'yourpassword'
}
resp = requests.post('https://github.com/session',
data=data, cookies=cookies)
print(resp.text)
if __name__ == '__main__':
main()
import robobrowser
def main():
b = robobrowser.RoboBrowser(parser='lxml')
b.open('https://github.com/login')
f = b.get_form(action='/session')
f['login'].value = 'jackfrued@gmail.com'
f['password'].value = 'yourpassword'
b.submit_form(f)
for a_tag in b.select('a[href]'):
print(a_tag.attrs['href'])
if __name__ == '__main__':
main()
import requests import robobrowser
from bs4 import BeautifulSoup
# selenium是一个自动化测试工具
# 通过它可以模拟浏览器的行为来访问Web页面
from selenium import webdriver
def main(): def main():
# 先下载chromedriver并且将可执行程序放到PATH环境变量路径下 b = robobrowser.RoboBrowser(parser='lxml')
# 创建谷歌Chrome浏览器内核 b.open('https://v.taobao.com/v/content/live?catetype=704&from=taonvlang')
driver = webdriver.Chrome() for img_tag in b.select('img[src]'):
# 通过浏览器内核加载页面(可以加载动态生成的内容) print(img_tag.attrs['src'])
driver.get('https://www.taobao.com/markets/mm/mm2017')
# driver.page_source获得的页面包含了JavaScript动态创建的内容
soup = BeautifulSoup(driver.page_source, 'lxml')
all_images = soup.select('img[src]')
for image in all_images:
url = image.get('src')
try:
if not str(url).startswith('http'):
url = 'http:' + url
filename = url[url.rfind('/') + 1:]
print(filename)
resp = requests.get(url)
with open('c:/images/' + filename, 'wb') as f:
f.write(resp.content)
except OSError:
print(filename + '下载失败!')
print('图片下载完成!')
if __name__ == '__main__': if __name__ == '__main__':
......
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
def main():
driver = webdriver.Chrome()
driver.get('https://v.taobao.com/v/content/live?catetype=704&from=taonvlang')
elem = driver.find_element_by_css_selector('input[placeholder=输入关键词搜索]')
elem.send_keys('运动')
elem.send_keys(Keys.ENTER)
soup = BeautifulSoup(driver.page_source, 'lxml')
for img_tag in soup.body.select('img[src]'):
print(img_tag.attrs['src'])
if __name__ == '__main__':
main()
import base64
from PIL import Image, ImageFilter
from pytesseract import image_to_string
import requests
from io import BytesIO
def main():
guido_img = Image.open(open('guido.jpg', 'rb'))
guido2_img = guido_img.filter(ImageFilter.GaussianBlur)
guido2_img.save(open('guido2.jpg', 'wb'))
img1 = Image.open(open('tesseract.png', 'rb'))
img2 = img1.point(lambda x: 0 if x < 128 else 255)
img2.save(open('tesseract2.png', 'wb'))
print(image_to_string(img2))
resp = requests.get('https://pin2.aliyun.com/get_img?type=150_40&identity=mailsso.mxhichina.com&sessionid=k0xHyBxU3K3dGXb59mP9cdeTXxL9gLHSTKhRZCryHxpOoyk4lAVuJhgw==')
img3 = Image.open(BytesIO(resp.content))
img3.save('captcha.jpg')
print(image_to_string(img3))
print(base64.b64encode(resp.content))
if __name__ == '__main__':
main()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment