ada/c22712
1
0
Fork 0
mirror of https://github.com/KUlishevgeniy/c22712.git synced 2026-09-23 23:50:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Парсинг

Browse Source
This commit is contained in:
Dronminator
2023-02-16 11:49:57 +03:00
parent 17d84ef8f1
commit 8fa857a7d5
2 changed files with 30 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.idea/workspace.xml
Generated
+16 -2
View File
@@ -5,8 +5,8 @@
</component>
<component name="ChangeListManager">
<list default="true" id="e5615680-c090-497d-a104-1337ed85f850" name="Changes" comment="Первый коммит">
<change afterPath="$PROJECT_DIR$/Задания/task1/Lahin/parsing.py" afterDir="false" />
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
<change beforePath="$PROJECT_DIR$/Задания/Lahin/test" beforeDir="false" />
</list>
<option name="SHOW_DIALOG" value="false" />
<option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -91,7 +91,21 @@
<option name="project" value="LOCAL" />
<updated>1675931967836</updated>
</task>
<option name="localTasksCounter" value="3" />
<task id="LOCAL-00003" summary="Первый коммит">
<created>1676532721150</created>
<option name="number" value="00003" />
<option name="presentableId" value="LOCAL-00003" />
<option name="project" value="LOCAL" />
<updated>1676532721150</updated>
</task>
<task id="LOCAL-00004" summary="Первый коммит">
<created>1676532798232</created>
<option name="number" value="00004" />
<option name="presentableId" value="LOCAL-00004" />
<option name="project" value="LOCAL" />
<updated>1676532798232</updated>
</task>
<option name="localTasksCounter" value="5" />
<servers />
</component>
<component name="TypeScriptGeneratedFilesManager">
Задания/task1/Lahin/parsing.py
+14
View File
@@ -0,0 +1,14 @@
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from time import sleep
s = Service("С:\DATA\ChromeDriver\chromedriver.exe")
browser = webdriver.Chrome(service=s)
browser.get("https://www.kinopoisk.ru/lists/movies/top250/")
sleep(15)
html_text = browser.page_source
soup = BeautifulSoup(html_text, 'lxml')
films = soup.find_all('div', class_="desktop-list-main-info_secondaryTitleSlot__mc0mI")
for film in films:
print(film.text)
print("--------")