v4l3n71n/web_scrap
1
0
Fork 0
Code Issues Pull Requests Projects Releases 10 Wiki Activity

distinct tags and categories

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-03-27 23:51:51 +02:00
parent 3622e37942
commit 0c41dc3e65
1 changed files with 33 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
insert_wordpress.py
View File

@ -3,7 +3,7 @@ from bs4 import BeautifulSoup
from urllib.parse import urlparse from urllib.parse import urlparse
from requests.auth import HTTPBasicAuth from requests.auth import HTTPBasicAuth
from getpass import getpass from getpass import getpass
import requests, os, argparse, logging import requests, os, argparse, logging, re
if __name__ == '__main__': if __name__ == '__main__':
@ -19,13 +19,19 @@ if __name__ == '__main__':
exit(1) exit(1)
basic = HTTPBasicAuth(args.user, password) basic = HTTPBasicAuth(args.user, password)
page = requests.get("http://localhost:8080/wp-json/wp/v2/tags") liste = ["categories", "tags"]
elements = {}
if page.status_code == 200: element = {}
tags = page.json() listelement = {}
print(tags)
for i in liste:
page = requests.get("http://localhost:8080/wp-json/wp/v2/{0}".format(i))
if page.status_code == 200:
elements[i] = page.json()
element[i] = []
listelement[i] = []
with open(args.file, 'r') as f: with open(args.file, 'r') as f:
contents = f.read() contents = f.read()
@ -36,34 +42,36 @@ if __name__ == '__main__':
dateheader = soup.find_all("div", class_="dateheader") dateheader = soup.find_all("div", class_="dateheader")
itemfooter = soup.find_all("div", class_="itemfooter") itemfooter = soup.find_all("div", class_="itemfooter")
a = itemfooter[0].find_all("a", {"rel": True}) a = itemfooter[0].find_all("a", {"rel": True})
tag = []
for i in a: for i in a:
rel = i.get("rel") rel = i.get("rel")
if rel[0] == 'tag': if rel[0] == 'tag':
tag.append(i.text) href = i.get("href")
listtag = [] if re.search(r'/tag/', href):
for i in tag: element["tags"].append(i.text)
tag_exist = False if re.search(r'/archives/', href):
for j in tags: element["categories"].append(i.text)
if j["name"] == i: for i in liste:
tag_exist = True for j in element[i]:
listtag.append(j["id"]) element_exist = False
if tag_exist is False: for k in elements[i]:
data = {"name": i} if k["name"] == j:
page = requests.post("http://localhost:8080/wp-json/wp/v2/tags", auth=basic, data=data) element_exist = True
if page.status_code == 201: array = listelement[i].append(k["id"])
result = page.json() if element_exist is False:
listtag.append(result["id"]) data = {"name": j}
page = requests.post("http://localhost:8080/wp-json/wp/v2/{0}".format(i), auth=basic, data=data)
if page.status_code == 201:
result = page.json()
listelement[i].append(result["id"])
title = articletitle[0].text title = articletitle[0].text
body = articlebody[0] body = articlebody[0]
hour = articledate[0].text hour = articledate[0].text
time = dateheader[0].text.split(" ") time = dateheader[0].text.split(" ")
data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listtag} data = {"title":title, "content":body, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
print(data)
exit(0)
page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data) page = requests.post("http://localhost:8080/wp-json/wp/v2/posts", auth=basic, data=data)
print(page.status_code) print(page.status_code)