Itmens/lib.itmens
Itmens/lib.itmens
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge pull request #33 from doubaniux/crawler

Browse source 
add click-to-scrape feature | close #9
This commit is contained in:
doubaniux 2020-05-12 14:12:41 +08:00 • committed by GitHub
commit 5e2720ebe3
12 changed files with 249 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
.gitignore vendored
View file

@ -18,5 +18,5 @@ migrations/
*.sqlite3
# deployed media and static files
.media/
.static/
media/
static/

4
books/forms.py
View file

@ -59,11 +59,13 @@ class BookForm(forms.ModelForm):
'brief': _("简介"),
'other_info': _("其他信息"),
}
from common.forms import ImageInput
widgets = {
'author': forms.TextInput(attrs={'placeholder': _("多个作者使用英文逗号分隔")}),
'translator': forms.TextInput(attrs={'placeholder': _("多个译者使用英文逗号分隔")}),
'other_info': KeyValueInput(),
'cover': forms.FileInput(),
# 'cover': forms.FileInput(),
'cover': ImageInput(),
}
def clean_isbn(self):

6
books/static/js/scrape.js
View file

@ -5,9 +5,9 @@ $(document).ready( function() {
});
// assume there is only one input[file] on page
$("input[type='file']").each(function() {
$(this).after('<img src="#" alt="" id="previewImage" style="margin:10px 0; max-width:500px;"/>');
});
// $("input[type='file']").each(function() {
// $(this).after('<img src="#" alt="" id="previewImage" style="margin:10px 0; max-width:500px;"/>');
// });
// preview uploaded pic
$("input[type='file']").change(function() {

17
books/templates/books/scrape.html
View file

@ -48,8 +48,9 @@
<section id="content" class="container">
<div class="row">
<div id="main">
<div class="set">
{% trans '根据豆瓣内容填写下方表单' %}
</div>
<iframe id='test' sandbox="allow-same-origin allow-scripts allow-popups allow-forms" src="https://search.douban.com/book/subject_search{% if q %}?search_text={{ q }}{% endif %}" frameborder="0"></iframe>
<div class="dividing-line"></div>
<div id="parser">
@ -81,11 +82,15 @@ ISBN: 9787020104345
<div id="aside">
<div class="aside-card">
<div class="add-nav">
<div>
{% trans '根据豆瓣内容填写下方表格！' %}
<div class="set">
{% trans '或者复制详情页链接' %}
</div>
<a href="{% url 'books:scrape' %}" class="button add-button submit">{% trans '剽取！' %}</a>
<form action="{% url 'books:click_to_scrape' %}" method="post">
{% csrf_token %}
<input type="text" name="url" required placeholder="https://book.douban.com/subject/1000000/">
<input type="submit" class="button add-button" value="{% trans '一键取剽取!' %}">
</form>
</div>
</div>

1
books/urls.py
View file

@ -17,4 +17,5 @@ urlpatterns = [
path('review/<int:id>/', retrieve_review, name='retrieve_review'),
path('<int:book_id>/review/list/', retrieve_review_list, name='retrieve_review_list'),
path('scrape/', scrape, name='scrape'),
path('click_to_scrape/', click_to_scrape, name='click_to_scrape'),
]

37
books/views.py
View file

@ -6,6 +6,7 @@ from django.core.exceptions import ObjectDoesNotExist, PermissionDenied
from django.db import IntegrityError, transaction
from django.utils import timezone
from django.core.paginator import Paginator
from django.core.files.uploadedfile import SimpleUploadedFile
from common.mastodon import mastodon_request_included
from common.mastodon.api import check_visibility, post_toot, TootVisibilityEnum
from common.mastodon.utils import rating_to_emoji
@ -454,5 +455,41 @@ def scrape(request):
'form': form,
}
)
else:
return HttpResponseBadRequest()
@login_required
def click_to_scrape(request):
if request.method == "POST":
url = request.POST.get("url")
if url:
from common.scraper import scrape_douban_book
try:
scraped_book, raw_cover = scrape_douban_book(url)
except TimeoutError:
return render(
request,
'common/error.html',
{
'msg': _("爬取数据失败😫"),
}
)
scraped_cover = {'cover': SimpleUploadedFile('temp.jpg', raw_cover)}
form = BookForm(scraped_book, scraped_cover)
if form.is_valid():
form.instance.last_editor = request.user
form.save()
return redirect(reverse('books:retrieve', args=[form.instance.id]))
else:
return render(
request,
'common/error.html',
{
'msg': _("爬取数据失败😫"),
}
)
else:
return HttpResponseBadRequest()
else:
return HttpResponseBadRequest()

18
common/forms.py
View file

@ -56,4 +56,20 @@ class RatingValidator:
raise ValidationError(
_('%(value)s is not an integer in range 1-10'),
params={'value': value},
)
)
class ImageInput(forms.FileInput):
template_name = 'widgets/image.html'
def format_value(self, value):
"""
Return the file object if it has a defined url attribute.
"""
if self.is_initial(value):
return value
def is_initial(self, value):
"""
Return whether value is considered to be initial value.
"""
return bool(value and getattr(value, 'url', False))

1
common/mastodon/auth.py
View file

@ -6,7 +6,6 @@ from .api import *
def obtain_token(request, code):
""" Returns token if success else None. """
# TODO change http!
payload = {
'client_id': CLIENT_ID,
'client_secret': CLIENT_SECRET,

163
common/scraper.py Normal file
View file

@ -0,0 +1,163 @@
import requests
import random
from lxml import html
import re
RE_NUMBERS = re.compile(r"\d+\d*")
RE_WHITESPACES = re.compile(r"\s+")
DEFAULT_REQUEST_HEADERS = {
'Host': 'book.douban.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:70.0) Gecko/20100101 Firefox/70.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
# well, since brotli lib is so bothering, remove `br`
'Accept-Encoding': 'gzip, deflate',
'Connection': 'keep-alive',
'DNT': '1',
'Upgrade-Insecure-Requests': '1',
'Cache-Control': 'max-age=0',
}
# in seconds
TIMEOUT = 10
# luminati account credentials
USERNAME = '***REMOVED***'
PASSWORD = '***REMOVED***'
PORT = 22225
def scrape_douban_book(url):
session_id = random.random()
proxy_url = ('http://%s-country-cn-session-%s:%s@zproxy.lum-superproxy.io:%d' %
(USERNAME, session_id, PASSWORD, PORT))
proxies = {
'http': proxy_url,
'https': proxy_url,
}
# r = requests.get(url, proxies=proxies, headers=DEFAULT_REQUEST_HEADERS, timeout=TIMEOUT)
r = requests.get(url, headers=DEFAULT_REQUEST_HEADERS, timeout=TIMEOUT)
content = html.fromstring(r.content.decode('utf-8'))
title = content.xpath("/html/body/div[3]/h1/span/text()")[0].strip()
subtitle_elem = content.xpath("//div[@id='info']//span[text()='副标题:']/following::text()")
subtitle = subtitle_elem[0].strip() if subtitle_elem else None
orig_title_elem = content.xpath("//div[@id='info']//span[text()='原作名:']/following::text()")
orig_title = orig_title_elem[0].strip() if orig_title_elem else None
language_elem = content.xpath("//div[@id='info']//span[text()='语言:']/following::text()")
language = language_elem[0].strip() if language_elem else None
pub_house_elem = content.xpath("//div[@id='info']//span[text()='出版社:']/following::text()")
pub_house = pub_house_elem[0].strip() if pub_house_elem else None
pub_date_elem = content.xpath("//div[@id='info']//span[text()='出版年:']/following::text()")
pub_date = pub_date_elem[0].strip() if pub_date_elem else None
year_month_day = RE_NUMBERS.findall(pub_date)
if len(year_month_day) in (2, 3):
pub_year = int(year_month_day[0])
pub_month = int(year_month_day[1])
elif len(year_month_day) == 1:
pub_year = int(year_month_day[0])
pub_month = None
else:
pub_year = None
pub_month = None
if pub_year and pub_month and pub_year < pub_month:
pub_year, pub_month = pub_month, pub_year
pub_year = None if pub_year is not None and not pub_year in range(0, 3000) else pub_year
pub_month = None if pub_month is not None and not pub_month in range(1, 12) else pub_month
binding_elem = content.xpath("//div[@id='info']//span[text()='装帧:']/following::text()")
binding = binding_elem[0].strip() if binding_elem else None
price_elem = content.xpath("//div[@id='info']//span[text()='定价:']/following::text()")
price = price_elem[0].strip() if price_elem else None
pages_elem = content.xpath("//div[@id='info']//span[text()='页数:']/following::text()")
pages = pages_elem[0].strip() if pages_elem else None
pages = int(RE_NUMBERS.findall(pages)[0]) if RE_NUMBERS.findall(pages) else None
isbn_elem = content.xpath("//div[@id='info']//span[text()='ISBN:']/following::text()")
isbn = isbn_elem[0].strip() if isbn_elem else None
brief_elem = content.xpath("//h2/span[text()='内容简介']/../following-sibling::div[1]//div[@class='intro']/p/text()")
brief = '\n'.join(p.strip() for p in brief_elem) if brief_elem else None
img_url_elem = content.xpath("//*[@id='mainpic']/a/img/@src")
img_url = img_url_elem[0].strip() if img_url_elem else None
raw_img = None
if img_url:
img_response = requests.get(
img_url,
headers={
'accept': 'image/webp,image/apng,image/*,*/*;q=0.8',
'accept-encoding': 'gzip, deflate',
'accept-language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7,fr-FR;q=0.6,fr;q=0.5,zh-TW;q=0.4',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36 Edg/81.0.416.72',
'cache-control': 'no-cache',
'dnt': '1' ,
},
# proxies=proxies,
timeout=TIMEOUT,
)
if img_response.status_code == 200:
raw_img = img_response.content
# there are two html formats for authors and translators
authors_elem = content.xpath("""//div[@id='info']//span[text()='作者:']/following-sibling::br[1]/
preceding-sibling::a[preceding-sibling::span[text()='作者:']]/text()""")
if not authors_elem:
authors_elem = content.xpath("""//div[@id='info']//span[text()=' 作者']/following-sibling::a/text()""")
if authors_elem:
authors = []
for author in authors_elem:
authors.append(RE_WHITESPACES.sub(' ', author.strip()))
else:
authors = None
translators_elem = content.xpath("""//div[@id='info']//span[text()='译者:']/following-sibling::br[1]/
preceding-sibling::a[preceding-sibling::span[text()='译者:']]/text()""")
if not translators_elem:
translators_elem = content.xpath("""//div[@id='info']//span[text()=' 译者']/following-sibling::a/text()""")
if translators_elem:
translators = []
for translator in translators_elem:
translators.append(RE_WHITESPACES.sub(' ', translator.strip()))
else:
translators = None
other = {}
cncode_elem = content.xpath("//div[@id='info']//span[text()='统一书号:']/following::text()")
if cncode_elem:
other['统一书号'] = cncode_elem[0].strip()
series_elem = content.xpath("//div[@id='info']//span[text()='丛书:']/following-sibling::a[1]/text()")
if series_elem:
other['丛书'] = series_elem[0].strip()
imprint_elem = content.xpath("//div[@id='info']//span[text()='出品方:']/following-sibling::a[1]/text()")
if imprint_elem:
other['出品方'] = imprint_elem[0].strip()
data = {
'title' : title,
'subtitle' : subtitle,
'orig_title' : orig_title,
'author' : authors,
'translator' : translators,
'language' : language,
'pub_house' : pub_house,
'pub_year' : pub_year,
'pub_month' : pub_month,
'binding' : binding,
'price' : price,
'pages' : pages,
'isbn' : isbn,
'brief' : brief,
'other_info' : other
}
return data, raw_img

6
common/static/js/create_update.js
View file

@ -1,8 +1,8 @@
$(document).ready( function() {
// assume there is only one input[file] on page
$("input[type='file']").each(function() {
$(this).after('<img src="#" alt="" id="previewImage" style="margin:10px 0; max-width:500px;"/>');
})
// $("input[type='file']").each(function() {
// $(this).after('<img src="#" alt="" id="previewImage" style="margin:10px 0; max-width:500px;"/>');
// })
// mark required
$("input[required]").each(function() {

2
common/templates/widgets/image.html Normal file
View file

@ -0,0 +1,2 @@
<input type="{{ widget.type }}" name="{{ widget.name }}"{% include "django/forms/widgets/attrs.html" %}>
<img src="{{ widget.value|default_if_none:''|stringformat:'s' }}" alt="" id="previewImage" style="margin:10px 0; max-width:500px;">

10
users/views.py
View file

@ -40,8 +40,13 @@ def OAuth2_login(request):
request.session['new_user_token'] = token
return redirect(reverse('users:register'))
else:
# TODO better fail result page
return HttpResponse(content="Authentication failed.")
return render(
request,
'common/error.html',
{
'msg': _("认证失败😫")
}
)
else:
return HttpResponseBadRequest()
@ -49,7 +54,6 @@ def OAuth2_login(request):
# the 'login' page that user can see
def login(request):
if request.method == 'GET':
# TODO NOTE replace http with https!!!!
auth_url = f"https://{MASTODON_DOMAIN_NAME}{API_OAUTH_AUTHORIZE}?" +\
f"client_id={CLIENT_ID}&scope=read+write&" +\
f"redirect_uri=https://{request.get_host()}{reverse('users:OAuth2_login')}" +\