-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
13 changed files
with
273 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
1.scrapy项目的结构 | ||
项目名字 | ||
项目名字 | ||
spiders文件夹(存储的是爬虫文件) | ||
init | ||
自定义的爬虫文件 核心功能文件************最重要的 | ||
init | ||
items 定义数据结构的地方 爬取的数据包含哪些 | ||
middlewares 中间件 代理 | ||
pipelines 管道 用来处理下载的数据 | ||
settings 配置文件 robots协议 ua定义 | ||
|
||
|
||
2.response的属性和方法 | ||
response.text 获取响应的字符串 | ||
response.body 获取二进制数据 | ||
response.xpath 可以直接使用xpath方法来解析response中的内容 | ||
response.extract() 提取selector对象的data属性值 | ||
response.extract_first() 提取的是selector列表的第一个数据 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,11 @@ | ||
# Automatically created by: scrapy startproject | ||
# | ||
# For more information about the [deploy] section see: | ||
# https://scrapyd.readthedocs.io/en/latest/deploy.html | ||
|
||
[settings] | ||
default = scrapy_58tc_037.settings | ||
|
||
[deploy] | ||
#url = http://localhost:6800/ | ||
project = scrapy_58tc_037 |
Empty file.
Binary file added
BIN
+182 Bytes
scrapy_58tc_037/scrapy_58tc_037/__pycache__/__init__.cpython-39.pyc
Binary file not shown.
Binary file added
BIN
+283 Bytes
scrapy_58tc_037/scrapy_58tc_037/__pycache__/settings.cpython-39.pyc
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,12 @@ | ||
# Define here the models for your scraped items | ||
# | ||
# See documentation in: | ||
# https://docs.scrapy.org/en/latest/topics/items.html | ||
|
||
import scrapy | ||
|
||
|
||
class Scrapy58Tc037Item(scrapy.Item): | ||
# define the fields for your item here like: | ||
# name = scrapy.Field() | ||
pass |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,103 @@ | ||
# Define here the models for your spider middleware | ||
# | ||
# See documentation in: | ||
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html | ||
|
||
from scrapy import signals | ||
|
||
# useful for handling different item types with a single interface | ||
from itemadapter import is_item, ItemAdapter | ||
|
||
|
||
class Scrapy58Tc037SpiderMiddleware: | ||
# 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 Scrapy58Tc037DownloaderMiddleware: | ||
# 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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
# Define your item pipelines here | ||
# | ||
# Don't forget to add your pipeline to the ITEM_PIPELINES setting | ||
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html | ||
|
||
|
||
# useful for handling different item types with a single interface | ||
from itemadapter import ItemAdapter | ||
|
||
|
||
class Scrapy58Tc037Pipeline: | ||
def process_item(self, item, spider): | ||
return item |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,88 @@ | ||
# Scrapy settings for scrapy_58tc_037 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 = 'scrapy_58tc_037' | ||
|
||
SPIDER_MODULES = ['scrapy_58tc_037.spiders'] | ||
NEWSPIDER_MODULE = 'scrapy_58tc_037.spiders' | ||
|
||
|
||
# Crawl responsibly by identifying yourself (and your website) on the user-agent | ||
#USER_AGENT = 'scrapy_58tc_037 (+http://www.yourdomain.com)' | ||
|
||
# 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://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 = { | ||
# 'scrapy_58tc_037.middlewares.Scrapy58Tc037SpiderMiddleware': 543, | ||
# } | ||
|
||
# Enable or disable downloader middlewares | ||
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html | ||
# DOWNLOADER_MIDDLEWARES = { | ||
# 'scrapy_58tc_037.middlewares.Scrapy58Tc037DownloaderMiddleware': 543, | ||
# } | ||
|
||
# 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 = { | ||
# 'scrapy_58tc_037.pipelines.Scrapy58Tc037Pipeline': 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' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
# 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. |
Binary file added
BIN
+190 Bytes
scrapy_58tc_037/scrapy_58tc_037/spiders/__pycache__/__init__.cpython-39.pyc
Binary file not shown.
Binary file added
BIN
+806 Bytes
scrapy_58tc_037/scrapy_58tc_037/spiders/__pycache__/tc.cpython-39.pyc
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,23 @@ | ||
import scrapy | ||
|
||
|
||
class TcSpider(scrapy.Spider): | ||
name = 'tc' | ||
allowed_domains = [ | ||
'https://wn.58.com/job/?key=%E5%89%8D%E7%AB%AF%E5%BC%80%E5%8F%91'] | ||
start_urls = [ | ||
'https://wn.58.com/job/?key=%E5%89%8D%E7%AB%AF%E5%BC%80%E5%8F%91/'] | ||
|
||
def parse(self, response): | ||
# print('山东菏泽曹县') | ||
# 获取字符串 | ||
# content = response.text | ||
# 获取二进制数据 | ||
# content = response.body | ||
|
||
print('================') | ||
# print(content) | ||
|
||
span = response.xpath('//div[@id="filterJob"]//li[@class="select"]')[0] | ||
print(span.extract()) | ||
# print(span) |