Facebook scraping

1 files changed, 0 insertions, 86 deletions

diff --git a/scraper.py b/scraper.py
deleted file mode 100644
index ee7dd8f..0000000
--- a/scraper.py
+++ /dev/null
@@ -1,86 +0,0 @@
-from selenium import webdriver
-from selenium.webdriver.support.wait import WebDriverWait
-from selenium.common.exceptions import TimeoutException,\
-    ElementNotVisibleException, NoSuchElementException
-from bs4 import BeautifulSoup, Tag
-
-import os.path
-
-
-class Driver:
-
-    def __init__(self, username, password):
-        self.driver = webdriver.PhantomJS()
-        self.username = username
-        self.password = password
-        self.__connect()
-
-    def __ajax_complete(self):
-        return 0 == self.driver.execute_script("return jQuery.active")
-
-    def __connect(self):
-        driver = self.driver
-        driver.get("http://twitter.com")
-        driver.find_element_by_id("signin-email").send_keys(self.username)
-        elem = driver.find_element_by_id("signin-password")
-        elem.send_keys(self.password)
-        elem.submit()
-
-    def __get_followers(self, username):
-        driver = self.driver
-        driver.get("https://twitter.com/{0}/followers".format(username))
-        try:
-            footer = driver.find_element_by_class_name("timeline-end")
-        except NoSuchElementException:
-            return
-
-        while True:
-            try:
-                if "has-more-items" not in footer.get_attribute("class"):
-                    break
-                footer.click()
-                try:
-                    WebDriverWait(driver,
-                                  5).until(lambda x: self.__ajax_complete(),
-                                           "Timeout waiting for "
-                                           "ajax to return")
-                except TimeoutException:
-                    break
-            except (NoSuchElementException, ElementNotVisibleException):
-                break
-
-        try:
-            fws = driver.find_element_by_id("stream-items-id")
-        except NoSuchElementException:
-            return
-
-        soup = BeautifulSoup(fws.get_attribute("outerHTML"))
-        for follower in soup.ol:
-            if type(follower) == Tag:
-                div = follower.div
-                user_id = div["data-user-id"]
-                screen_name = div["data-screen-name"]
-                yield user_id, screen_name
-
-    def get_followers(self, user_id, username):
-        filename = os.path.join("data", "users", user_id + ".txt")
-        if os.path.isfile(filename):
-            return filename
-        l = list(self.__get_followers(username))
-        with open(filename, "w") as f:
-            for (fid, fname) in l:
-                f.write(fid + " " + fname + "\n")
-        return filename
-
-    def process(self, filename):
-        with open(filename) as f:
-            for line in f:
-                values = line.strip().split()
-                self.get_followers(*values[:2])
-
-
-if __name__ == "__main__":
-    credentials = open("scraping_accounts.txt").readline().strip().split()
-    driver = Driver(*credentials[:2])
-    # driver.get_followers("23302126", "flipper509")
-    print driver.get_profile(100, "thibauthorel")