Created
May 28, 2018 17:45
-
-
Save nruigrok/b40f310cf9a02aa2445c91598adeed57 to your computer and use it in GitHub Desktop.
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
from lxml import html | |
import requests | |
import csv | |
import sys | |
import json | |
from amcatclient import AmcatAPI | |
import urllib | |
from lxml.html import fromstring | |
import time | |
from urllib.request import Request, urlopen | |
#headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'} | |
def gettree(s, url): | |
r2 = s.get(url, headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}) | |
while r2.status_code==429: | |
print("429 reached, waiting one minute") | |
time.sleep(60) | |
r2 = s.get(url) | |
while r2.status_code == 403: | |
print("403 reached, waiting one minute") | |
time.sleep(10) | |
r2 = s.get(url) | |
if r2.status_code !=200: | |
raise Exception("status code {},url:{}".format(r2.status_code, url)) | |
open("/tmp/test.html","w").write(r2.text) | |
tree = html.fromstring(r2.text) | |
tree.make_links_absolute(url) | |
return tree | |
def wijnartikel(url): | |
print(url) | |
regtree = gettree(s,url) | |
wijntxt = regtree.cssselect('div.main-body-text p') | |
if not wijntxt: | |
wijntxt =regtree.cssselect('div.main-body-text span') | |
if not wijntxt: | |
inhoud = "(no text)" | |
for wtxt in wijntxt: | |
inhoud = wtxt.text_content().strip() | |
if not inhoud: | |
inhoud = "(no text)" | |
wdict={} | |
k = regtree.cssselect('table.learn-table tr') | |
for item in k: | |
tds = item.cssselect("td") | |
key = tds[0].text_content().strip() | |
value = tds[1].text_content().strip() | |
wdict[key] = value | |
producer = wdict.get("Producer") | |
appellation = wdict.get("Appellation") | |
datum = "%s-01-01T00:00" % wdict['Vintage'].replace("NV","1900").replace("??","1900").replace("70/71","70") | |
art = {"title":"%s : %s" %(appellation, producer), | |
"text":inhoud, | |
"date":datum, | |
"author":wdict['Reviewer'], | |
"url":url} | |
if "Country" in wdict: | |
art["Country"]=wdict["Country"] | |
if 'Alcohol' in wdict and wdict['Alcohol'] != '': | |
art["Alcohol_num"]=int(float(wdict['Alcohol'].replace("%","")) * 10) | |
if 'Score' in wdict and wdict['Score'] != '?': | |
art["Score_num"] = int(float(wdict.get('Score','0').replace("??","0").replace("?","").replace(",",".").replace("_","").replace("!","").replace(".%","").replace("+","").replace("-","")) * 10) | |
if "When to drink" in wdict: | |
art["Whentodrink"]= wdict['When to drink'] | |
return art | |
conn = AmcatAPI("https://amcat.nl", "nel","S!nterklaas") | |
#conn = AmcatAPI("http://localhost:8000", "amcat","amcat") | |
s = requests.Session() | |
respons=s.get("http://www.jancisrobinson.com") | |
respons=s.post("http://www.jancisrobinson.com", data={"username": "nelruigrok@nieuwsmonitor.org", "password": "sinterklaas"}) | |
p=range(1,500) | |
#http://www.jancisrobinson.com/tastings/view/568013?from_search%5Bperpage%5D=100&from_search%5Bpage%5D=51&search_position=5062 | |
#url="http://www.jancisrobinson.com/tastings/view/568006?from_search%5Bperpage%5D=100&from_search%5Bpage%5D=51&search_position=5063" | |
#wijnartikel(url) | |
#sys.exit() | |
for pag in p: | |
tree = gettree(s,"http://www.jancisrobinson.com/tastings/search?perpage=100&page=%s" %(pag)) | |
print(tree) | |
a = tree.cssselect("h2") | |
print(a) | |
w =[] | |
for art in a: | |
wijn = wijnartikel(art.get("href")) | |
print(wijn) | |
w.append(wijn) | |
print(wijn) | |
articles = conn.create_articles(project=1039, articleset=73420, json_data=[wijn]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment