Das deutsche Python-Forum

Code: Alles auswählen

class Anfang():
    def __init__(self, url):
        self.url = url

    def seite1(self, url):
        url = "www"

    def seite2(self, url):
        return url

k = Anfang
print (k.seite2)



#Aktuelle Ausgabe:
<function Anfang.seite2 at 0x7f2774537f80>

#Gewünschte Ausgabe:
www

Code: Alles auswählen

class Anfang():
    def __init__(self, url=""):
        self.url = url

    def seite1(self):
        self.url = "www"

    def seite2(self):
        self.seite1()
        return self.url

k = Anfang()
print(k.seite2())

Code: Alles auswählen

#!/usr/bin/env python
import sys
import mysql.connector as mc

import requests
from bs4 import BeautifulSoup # sudo pacman -S python-p # sudo pip install beautifulsoup4
from urllib.parse import urljoin

url_start_item = "https://www.themoviedb.org"

url_start="https://www.themoviedb.org/search/movie?query="
url_end="&language=de-DE"


try:
	connection = mc.connect (host = "localhost",
							user = "mysql",
							passwd = "************",
							db = "Video_Database")


	cursor = connection.cursor()
	#cursor.execute("SELECT fi_title, fi_year FROM Video_Database.Movies WHERE `fi_fileID`='1' AND `fi_TMDb_Title` IS NULL")
	cursor.execute("SELECT fi_title, fi_year FROM Video_Database.Movies WHERE `fi_fileID`='1'")

	#cursor.execute("SELECT * FROM Video_Database.Movies")
	print('''Result of "SELECT fi_title, fi_year FROM Video_Database.Movies":''')
	result = cursor.fetchall() 
	
	
	for r in result:
		title=r[0].replace(" ", "%20")
		title2=r[0]
		year=r[1]
		url_full=url_start + title + "%20y:" + str(year) + url_end
		print(title2)
		#print(url_full)
		#continue
		r = requests.get(url_full)
		doc = BeautifulSoup(r.text, "html.parser")

		#####################################################
		#Teil1
		class CrawledArticle():
			def __init__(self, title, title2, id_num, full_url, item_url, content, release, release_year, image1, image2, counter):
				self.title = title
				self.id_num = id_num
				self.full_url = full_url
				self.item_url = item_url
				self.content = content
				self.release = release
				self.image1 = image1
				self.image2 = image2
				self.counter = counter
				self.release_year = release_year
				self.title2 = title2

			def fetch():
				counter = 0
				articles = []
				for card in doc.select(".card"):
					counter += 1

					image  = card.select_one(".image .poster .result img")
					if image is not None:
						image  = image.attrs["data-srcset"].split(",")
						image1 = image[0].replace("1x", "").replace(" ", "")
						image2 = image[1].replace("2x", "").replace(" ", "")
					else:
						image1 = "kein Bild"
						image2 = ""

					content = card.select_one(".overview").text.strip()
					if content == "":
						content = "kein Inhalt"
					title = card.select_one("h2").text
					#release = card.select_one(".release_date").text

					release = card.select_one(".release_date")
					if release is not None:
						release = release.text.strip()
					else:
						release = "k.A"

					release_year = release.split(" ")[2]

					item_url = card.select_one(".result").attrs["href"]
					item_url = url_start_item + item_url
					id_num = item_url.split("/")[4].split("?")[0]
					full_url = url_full

					crawled = CrawledArticle(title, title2, id_num, full_url, item_url, content, release, release_year, image1, image2, counter)
					articles.append(crawled)

				return articles
		################################################################################

		# Teil 2: Item
		class CrawledItem():
			url = "https://www.themoviedb.org/movie/97-tron?language=de-DE"
			r_item = requests.get(url)
			doc = BeautifulSoup(r_item.text, "html.parser")

			def __init__(self, image1, image2, genres_list, act_list):
				self.image1 = image1
				self.image2= image2
				self.genres_list = genres_list
				self.act_list = act_list

			def item_crawler():
				item_list = []
				for card in doc.select(".inner_content"):
					#Bild
					image = card.select_one("#main .content .poster .poster")
					if image is not None:
						image = image.attrs["srcset"].split(",")
						image1 = image[0].replace("1x", "").replace(" ", "")
						image2 = image[1].replace("2x", "").replace(" ", "")
					else:
						image1 = "kein Bild"
						image2 = "kein Bild"

					#Genres
					genres_list = []
					genres = card.select(".genres a")
					genres_num = len(genres)
					genres_count = 0
					for i in range(0, genres_num):
						genres_list.append(genres[i].text)

					#Darsteller
					#i=5
					act_list = []
					act_len = len(card.select(".card .character"))
					#print(act_len)
					for act_num in range(0, act_len):
						#act_num=7
						act_name = card.select(".card p a")[act_num].text
						act_list.append(act_name)




					crawled = CrawledItem(image1, image2, genres_list, act_list)
					item_list.append(crawled)
				return item_list
		################################################################################
		item = CrawledItem.item_crawler()

		for item2 in item:
			print(item2.image1)
			print(item2.image2)
			print(item2.genres_list)
			print(item2.act_list)
			print("Test")



		################################################################################

		articles = CrawledArticle.fetch()

		for article in articles:
			sql_update_query = """UPDATE `Video_Database`.`Movies` SET `fi_TMDb_ID`=%s,`fi_TMDb_Title`=%s WHERE `fi_title`=%s AND `fi_year`=%s"""
			input = (article.id_num,article.title, article.title2, article.release_year)

			cursor.execute(sql_update_query, input)
			#connection.commit()


			sql_update_query = """UPDATE `Video_Database`.`Movies` SET `fi_TMDb_content`=%s WHERE `fi_title`=%s AND `fi_year`=%s AND `fi_fileID`=1"""
			input = (article.content, article.title2, article.release_year)

			cursor.execute(sql_update_query, input)
			connection.commit()

			print("Record Updated successfully ")

			#break


#except mc.Error as e:
    #print("Error %d: %s" % (e.args[0], e.args[1]))
    #sys.exit(1)


except mysql.connector.Error as error:
    print("Failed to update record to database: {}".format(error))



finally:
    if (connection.is_connected()):
        connection.close()
        print("MySQL connection is closed")
#https://www.themoviedb.org/search/movie?query=Der%20Junge%20im%20gestreiften%20Pyjama&language=de-DE

Code: Alles auswählen

Titel und Jahr stehen schon in der Datenbank
Ich gehe zu dem Datensatz in der Datenbank der NULL ist
cursor.execute("SELECT fi_title, fi_year FROM Video_Database.Movies WHERE `fi_file_id`='1' AND `fi_TMDb_id` IS NULL")
Aus diesem Datensatz ziehe ich Titel und Jahr
Titel und Jahr übergebe ich dann an eine Funktion als Argument?

In der Funktion baue ich die URL zusammen die aus Titel und Jahr besteht.
      Mit der URL ziehe ich die Infos aus der Seite.
      Und speicher diese in dem Datensatz ab oder lieber erst mal in eine Variable?

Code: Alles auswählen

import requests
from bs4 import BeautifulSoup

def get_info(title, year):
    url_fl = "https://www.themoviedb.org/search/movie?query=" + title + "%20y:" + year + "&language=de-DE"
    req = requests.get(url_fl)
    doc = BeautifulSoup(req.text, "html.parser")
    
    for card in doc.select(".card"):
        #Titel
        title = card.select_one("h2").text

        #ItemURL
        item_url = card.select_one(".result").attrs["href"]

        items = {"Titel": title, "Item_URL": item_url}
        return items


film_info = get_info("Tron", "2010")
   
print(film_info["Titel"])
print(film_info["Item_URL"])

Code: Alles auswählen

#!/usr/bin/env python3
import requests
from bs4 import BeautifulSoup


def get_info(title, year):
    response = requests.get(
        "https://www.themoviedb.org/search/movie",
        params={"query": f"{title} y:{year}", "language": "de-DE"},
    )
    response.raise_for_status()
    doc = BeautifulSoup(response.text, "html.parser")
    card = doc.select_one(".card")
    if not card:
        return None

    return (
        card.select_one("h2").text,
        card.select_one(".result").get("href"),
    )
    


def main():
    print(get_info("Tron", "2010"))


if __name__ == "__main__":
    main()

Code: Alles auswählen

#!/usr/bin/env python
from module import get_infos as hole
from module import verbinden as schreibe

ausgabe = hole.get_info("Tron", "2010")
schreibe.connection(ausgabe) 


print(ausgabe)
('TRON: Legacy', '/movie/20526?language=de-DE', '20526', '10. Dezember 2010', 'https://image.tmdb.org/t/p/w94_and_h141_bestv2/okpodI7zyPwWsAm2yF5yva6Ea5h.jpg', 'https://image.tmdb.org/t/p/w188_and_h282_bestv2/okpodI7zyPwWsAm2yF5yva6Ea5h.jpg', '21 Jahre nach dem mysteriösen Verschwinden seines Vaters folgt Sam Flynn dem Lockruf eines Pagersignals und wird in die digitale Computerwelt des "Grid" hineingezogen. Dort hat Clu, das einst von seinem Vater geschaffene Programm, die Macht übernommen, dort verstecken sich auch Kevin Flynn und sein Protegé, das Programm Quorra. Nachdem Vater und Sohn sich wiedergefunden haben, verfolgen sie nur ein Ziel, wollen das Grid verlassen. Doch genau das will auch Clu, um seine Diktatur auf die Welt der User auszudehnen.', '2010')

Code: Alles auswählen

schreibe.connection(ausgabe,2,3,4,5,6,7,8)