进行大数据爬取数据，存入Mongodb

爬虫刚入门，对赶集网进行一次所有商品大数据的爬取

使用了多线程，存到数据库里，目前不知道要爬多久

有一个要注意的地方，比如我们要进行两次爬虫，一次是把每个项目的链接爬下来，一次是把每个项目里的详情信息爬下来，最好是先把每个项目的链接存下来，并用数据库保存，然后再从数据库取出每个链接，进行爬取详情信息。不要每爬到一个链接，就进去把这个链接的信息爬出来，这样不仅速度变慢，往往在爬取详情信息过程中会发生网络超时等断开爬虫的情况，如果是每次爬取链接都去取信息，那么一旦爬虫断了，每次都要重新开始

from multiprocessing import Pool
from channel_extract import channel
from page_parsing import get_item_info, get_links

def get_all_link_from(channel):
for i in range(1, 100):
get_links(channel, i)

if __name__ == '__main__':
pool = Pool()
pool.map(get_all_link_from, channel.split())
pool.close()
pool.join()

import time
from page_parsing import url_list

while True:
print(url_list.find().count())
time.sleep(5)

from bs4 import BeautifulSoup
import requests
import time

url = 'http://bj.ganji.com/wu/'
host_url = 'http://bj.ganji.com'
def get_channel(url):
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text, 'lxml')
links = soup.select('div > div > dl > dt > a')
for link in links:
new_url = host_url + link.get('href')
print(new_url)

get_channel(url)

channel = ''' http://bj.ganji.com/jiaju/ http://bj.ganji.com/rirongbaihuo/ http://bj.ganji.com/shouji/ http://bj.ganji.com/shoujihaoma/ http://bj.ganji.com/bangong/ http://bj.ganji.com/nongyongpin/ http://bj.ganji.com/jiadian/ http://bj.ganji.com/ershoubijibendiannao/ http://bj.ganji.com/ruanjiantushu/ http://bj.ganji.com/yingyouyunfu/ http://bj.ganji.com/diannao/ http://bj.ganji.com/xianzhilipin/ http://bj.ganji.com/fushixiaobaxuemao/ http://bj.ganji.com/meironghuazhuang/ http://bj.ganji.com/shuma/ http://bj.ganji.com/laonianyongpin/ http://bj.ganji.com/xuniwupin/ http://bj.ganji.com/qitawupin/ http://bj.ganji.com/ershoufree/ http://bj.ganji.com/wupinjiaohuan/
'''

from bs4 import BeautifulSoup
import requests
import time
import pymongo
import random

client = pymongo.MongoClient('localhost', 27017)
ganji = client['gangji']
url_list = ganji['url_list']
item_info = ganji['item_info']

headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.87 Safari/537.36',
'Connection':'keep-alive'
}

proxy_list = [
'http://101.4.136.34:81',
'http://182.96.194.184:8118'
]
proxy_ip = random.choice(proxy_list)
proxies = {'http':proxy_ip}

def get_links(channel,  page):
list_view = '{}o{}'.format(channel, page)
wb_data = requests.get(list_view)
soup = BeautifulSoup(wb_data.text, 'lxml')
links = soup.select('td.t > a.t')
if(soup.find('td', 't')):
for link in links:
new_url = str(link.get('href').split('?')[0])
url_list.insert_one({'url':new_url})
else:
pass

def get_item_info(url):
wb_data = requests.get(url, headers = headers, proxies = proxies)
soup = BeautifulSoup(wb_data.text, 'lxml')
no_longer_exist = (wb_data.status_code == 404)
if no_longer_exist:
pass
else:
try:
title = soup.title.text
price = soup.select('span.price_now > i')[0].get_text()
area = soup.select('div.palce_li > span > i')[0].get_text()
data = {
'title':title,
'price':price,
'area' :area
}
print(data)
except (AttributeError, IndexError):
pass