Crawl DxOMark Mobile (smartphones camera benchmark) data: https://de-novo.org/2017/12/29/efa로-내게-맞는-스마트폰-카메라-찾기/
import re | |
import requests | |
import datetime as dt | |
from bs4 import BeautifulSoup | |
# Crawl DxOMark Mobile data | |
class DxOCrawler(): | |
def __init__(self): | |
self.baseurl = "https://www.dxomark.com/category/mobile-reviews/page" | |
self.links = [] | |
self.data = dict() | |
def get(self): | |
for i in range(1, 12): | |
page = requests.get(self.baseurl + str(i)).content | |
soup = BeautifulSoup(page) | |
divs = soup.div | |
self.links += re.findall('<a class="plain" href=.+"', str(divs)) | |
self.links = [link[23:-1] for link in self.links] | |
for link in self.links: | |
#time.sleep(0.1) | |
article = requests.get(link).content | |
soup = BeautifulSoup(article) | |
try: | |
model = soup.find_all("div", attrs={"class": "scoreType photo"})[0].string | |
if model == "\n photo ": model = " ".join(soup.title.string.split()[:6]) | |
print model | |
photo, video = soup.find_all("div", attrs={"class": "anychart"}) | |
try: | |
photo = map(int, photo["data-array"].split(",")) | |
video = map(int, video["data-array"].split(",")) | |
except: | |
photo = photo["data-array"].split(",") | |
photo = map(int, photo[:-1]) + [photo[-1]] | |
video = map(int, video["data-array"].split(",")) | |
self.data[model] = photo + video | |
print photo + video | |
except IndexError: | |
print link | |
if __name__ == "__main__": | |
crawler = DxOCrawler() | |
crawler.get() | |
with open("DxOMark_mobile_{}.txt".format(str(dt.datetime.today().date())), "w") as w: | |
for k, v in crawler.data.items(): | |
v_tabbed = "\t".join(v) | |
w.write("{}\t{}\n".format(k, v_tabbed) |
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment