git-sync/crawlab
1
0
Fork 0
mirror of https://github.com/crawlab-team/crawlab.git synced 2026-01-22 17:31:03 +01:00
Code Issues Packages Projects Releases Wiki Activity

code cleanup

Browse Source
This commit is contained in:
Marvin Zhang
2019-07-23 21:10:52 +08:00
parent 0bd721795b
commit f287278fba
14 changed files with 0 additions and 553 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
deployfile/5ca468298ffaed82c65f0f90/juejin_spider 2.js
View File

@@ -1,82 +0,0 @@
const puppeteer = require('puppeteer');
const MongoClient = require('mongodb').MongoClient;
(async () => {
// browser
const browser = await (puppeteer.launch({
headless: true
}));
// define start url
const url = 'https://juejin.im';
// start a new page
const page = await browser.newPage();
// navigate to url
try {
await page.goto(url, {waitUntil: 'domcontentloaded'});
await page.waitFor(2000);
} catch (e) {
console.error(e);
// close browser
browser.close();
// exit code 1 indicating an error happened
code = 1;
process.emit("exit ");
process.reallyExit(code);
return
}
// scroll down to fetch more data
for (let i = 0; i < 100; i++) {
console.log('Pressing PageDown...');
await page.keyboard.press('PageDown', 200);
await page.waitFor(100);
}
// scrape data
const results = await page.evaluate(() => {
let results = [];
document.querySelectorAll('.entry-list > .item').forEach(el => {
if (!el.querySelector('.title')) return;
results.push({
url: 'https://juejin.com' + el.querySelector('.title').getAttribute('href'),
title: el.querySelector('.title').innerText
});
});
return results;
});
// open database connection
const client = await MongoClient.connect('mongodb://192.168.99.100:27017');
let db = await client.db('crawlab_test');
const colName = process.env.CRAWLAB_COLLECTION || 'results_juejin';
const taskId = process.env.CRAWLAB_TASK_ID;
const col = db.collection(colName);
// save to database
for (let i = 0; i < results.length; i++) {
// de-duplication
const r = await col.findOne({url: results[i]});
if (r) continue;
// assign taskID
results[i].task_id = taskId;
results[i].source = 'juejin';
// insert row
await col.insertOne(results[i]);
}
console.log(`results.length: ${results.length}`);
// close database connection
client.close();
// shutdown browser
browser.close();
})();

82
deployfile/5ca468298ffaed82c65f0f90/juejin_spider.js
View File

@@ -1,82 +0,0 @@
const puppeteer = require('puppeteer');
const MongoClient = require('mongodb').MongoClient;
(async () => {
// browser
const browser = await (puppeteer.launch({
headless: true
}));
// define start url
const url = 'https://juejin.im';
// start a new page
const page = await browser.newPage();
// navigate to url
try {
await page.goto(url, {waitUntil: 'domcontentloaded'});
await page.waitFor(2000);
} catch (e) {
console.error(e);
// close browser
browser.close();
// exit code 1 indicating an error happened
code = 1;
process.emit("exit ");
process.reallyExit(code);
return
}
// scroll down to fetch more data
for (let i = 0; i < 100; i++) {
console.log('Pressing PageDown...');
await page.keyboard.press('PageDown', 200);
await page.waitFor(100);
}
// scrape data
const results = await page.evaluate(() => {
let results = [];
document.querySelectorAll('.entry-list > .item').forEach(el => {
if (!el.querySelector('.title')) return;
results.push({
url: 'https://juejin.com' + el.querySelector('.title').getAttribute('href'),
title: el.querySelector('.title').innerText
});
});
return results;
});
// open database connection
const client = await MongoClient.connect('mongodb://127.0.0.1:27017');
let db = await client.db('crawlab_test');
const colName = process.env.CRAWLAB_COLLECTION || 'results_juejin';
const taskId = process.env.CRAWLAB_TASK_ID;
const col = db.collection(colName);
// save to database
for (let i = 0; i < results.length; i++) {
// de-duplication
const r = await col.findOne({url: results[i]});
if (r) continue;
// assign taskID
results[i].task_id = taskId;
results[i].source = 'juejin';
// insert row
await col.insertOne(results[i]);
}
console.log(`results.length: ${results.length}`);
// close database connection
client.close();
// shutdown browser
browser.close();
})();

0
deployfile/5ca46b508ffaed82c65f0f9c/juejin/__init__.py
View File

17
deployfile/5ca46b508ffaed82c65f0f9c/juejin/items.py
View File

@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class JuejinItem(scrapy.Item):
# define the fields for your item here like:
_id = scrapy.Field()
title = scrapy.Field()
link = scrapy.Field()
like = scrapy.Field()
task_id = scrapy.Field()

56
deployfile/5ca46b508ffaed82c65f0f9c/juejin/middlewares.py
View File

@@ -1,56 +0,0 @@
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class JuejinSpiderMiddleware(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)

25
deployfile/5ca46b508ffaed82c65f0f9c/juejin/pipelines.py
View File

@@ -1,25 +0,0 @@
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import os
from pymongo import MongoClient
MONGO_HOST = '127.0.0.1'
MONGO_PORT = 27017
MONGO_DB = 'crawlab_test'
class JuejinPipeline(object):
mongo = MongoClient(host=MONGO_HOST, port=MONGO_PORT)
db = mongo[MONGO_DB]
col_name = os.environ.get('CRAWLAB_COLLECTION','test')
col = db[col_name]
def process_item(self, item, spider):
item['task_id'] = os.environ.get('CRAWLAB_TASK_ID')
self.col.save(item)
return item

89
deployfile/5ca46b508ffaed82c65f0f9c/juejin/settings.py
View File

@@ -1,89 +0,0 @@
# -*- coding: utf-8 -*-
# Scrapy settings for juejin project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'juejin'
SPIDER_MODULES = ['juejin.spiders']
NEWSPIDER_MODULE = 'juejin.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
# 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 http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
# 'juejin.middlewares.JuejinSpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# 'juejin.middlewares.MyCustomDownloaderMiddleware': 543,
# }
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
# }
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'juejin.pipelines.JuejinPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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'

4
deployfile/5ca46b508ffaed82c65f0f9c/juejin/spiders/__init__ 2.py
View File

@@ -1,4 +0,0 @@
# 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.

4
deployfile/5ca46b508ffaed82c65f0f9c/juejin/spiders/__init__.py
View File

@@ -1,4 +0,0 @@
# 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.

17
deployfile/5ca46b508ffaed82c65f0f9c/juejin/spiders/juejin_spider.py
View File

@@ -1,17 +0,0 @@
# -*- coding: utf-8 -*-
import scrapy
from juejin.items import JuejinItem
class JuejinSpiderSpider(scrapy.Spider):
name = 'juejin_spider'
allowed_domains = ['juejin.com']
start_urls = ['https://juejin.im/search?query=celery']
def parse(self, response):
for item in response.css('ul.main-list > li.item'):
yield JuejinItem(
title=item.css('.title span').extract_first(),
link=item.css('a::attr("href")').extract_first(),
like=item.css('.like .count::text').extract_first(),
)

11
deployfile/5ca46b508ffaed82c65f0f9c/scrapy.cfg
View File

@@ -1,11 +0,0 @@
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = juejin.settings
[deploy]
#url = http://localhost:6800/
project = juejin

2
deployfile/5ca46b508ffaed82c65f0f9c/start.py
View File

@@ -1,2 +0,0 @@
from scrapy import cmdline
cmdline.execute(["scrapy","crawl","juejin_spider"])

82
deployfile/5ca46b508ffaed82c65f0fa0/juejin_spider 2.js
View File

@@ -1,82 +0,0 @@
const puppeteer = require('puppeteer');
const MongoClient = require('mongodb').MongoClient;
(async () => {
// browser
const browser = await (puppeteer.launch({
headless: true
}));
// define start url
const url = 'https://juejin.im';
// start a new page
const page = await browser.newPage();
// navigate to url
try {
await page.goto(url, {waitUntil: 'domcontentloaded'});
await page.waitFor(2000);
} catch (e) {
console.error(e);
// close browser
browser.close();
// exit code 1 indicating an error happened
code = 1;
process.emit("exit ");
process.reallyExit(code);
return
}
// scroll down to fetch more data
for (let i = 0; i < 100; i++) {
console.log('Pressing PageDown...');
await page.keyboard.press('PageDown', 200);
await page.waitFor(100);
}
// scrape data
const results = await page.evaluate(() => {
let results = [];
document.querySelectorAll('.entry-list > .item').forEach(el => {
if (!el.querySelector('.title')) return;
results.push({
url: 'https://juejin.com' + el.querySelector('.title').getAttribute('href'),
title: el.querySelector('.title').innerText
});
});
return results;
});
// open database connection
const client = await MongoClient.connect('mongodb://127.0.0.1:27017');
let db = await client.db('crawlab_test');
const colName = process.env.CRAWLAB_COLLECTION || 'results_juejin';
const taskId = process.env.CRAWLAB_TASK_ID;
const col = db.collection(colName);
// save to database
for (let i = 0; i < results.length; i++) {
// de-duplication
const r = await col.findOne({url: results[i]});
if (r) continue;
// assign taskID
results[i].task_id = taskId;
results[i].source = 'juejin';
// insert row
await col.insertOne(results[i]);
}
console.log(`results.length: ${results.length}`);
// close database connection
client.close();
// shutdown browser
browser.close();
})();

82
deployfile/5ca46b508ffaed82c65f0fa0/juejin_spider.js
View File

@@ -1,82 +0,0 @@
const puppeteer = require('puppeteer');
const MongoClient = require('mongodb').MongoClient;
(async () => {
// browser
const browser = await (puppeteer.launch({
headless: true
}));
// define start url
const url = 'https://juejin.im';
// start a new page
const page = await browser.newPage();
// navigate to url
try {
await page.goto(url, {waitUntil: 'domcontentloaded'});
await page.waitFor(2000);
} catch (e) {
console.error(e);
// close browser
browser.close();
// exit code 1 indicating an error happened
code = 1;
process.emit("exit ");
process.reallyExit(code);
return
}
// scroll down to fetch more data
for (let i = 0; i < 100; i++) {
console.log('Pressing PageDown...');
await page.keyboard.press('PageDown', 200);
await page.waitFor(100);
}
// scrape data
const results = await page.evaluate(() => {
let results = [];
document.querySelectorAll('.entry-list > .item').forEach(el => {
if (!el.querySelector('.title')) return;
results.push({
url: 'https://juejin.com' + el.querySelector('.title').getAttribute('href'),
title: el.querySelector('.title').innerText
});
});
return results;
});
// open database connection
const client = await MongoClient.connect('mongodb://127.0.0.1:27017');
let db = await client.db('crawlab_test');
const colName = process.env.CRAWLAB_COLLECTION || 'results_juejin';
const taskId = process.env.CRAWLAB_TASK_ID;
const col = db.collection(colName);
// save to database
for (let i = 0; i < results.length; i++) {
// de-duplication
const r = await col.findOne({url: results[i]});
if (r) continue;
// assign taskID
results[i].task_id = taskId;
results[i].source = 'juejin';
// insert row
await col.insertOne(results[i]);
}
console.log(`results.length: ${results.length}`);
// close database connection
client.close();
// shutdown browser
browser.close();
})();